2008.bib

@comment{{This file has been generated by bib2bib 1.92}}
@comment{{Command line: /home/korin/bibtex2html-1.92-LINUX/bib2bib -oc /home/korin/projects/publications/new_output/transitdata/2008-citations -ob /home/korin/projects/publications/new_output/transitdata/2008.bib -c 'year : "2008"' /home/korin/projects/publications/filtlists/full_publications_list.bib}}
@article{analysis-hts-adaptation-junichi,
  author = {Yamagishi, Junichi and Kobayashi, Takao and Nakano, Yuji and Ogata, Katsumi and Isogai, Juri},
  title = {Analysis of Speaker Adaptation Algorihms for {HMM}-based Speech Synthesis and a Constrained {SMAPLR} Adaptation Algorithm},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  note = {In print},
  key = {analysis-hts-adaptation-junichi},
  year = {2008},
  abstract = {In this paper we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structural maximum a posteriori linear regression (CSMAPLR) whose derivation is based on the knowledge obtained in this analysis and on the results of comparing several conventional adaptation algorithms. Here we investigate six major aspects of the speaker adaptation: initial models transform functions, estimation criteria, and sensitivity of several linear regression adaptation algorithms algorithms. Analyzing the effect of the initial model, we compare speaker-dependent models, gender-independent models, and the simultaneous use of the gender-dependent models to single use of the gender-dependent models. Analyzing the effect of the transform functions, we compare the transform function for only mean vectors with that for mean vectors and covariance matrices. Analyzing the effect of the estimation criteria, we compare the ML criterion with a robust estimation criterion called structural MAP. We evaluate the sensitivity of several thresholds for the piecewise linear regression algorithms and take up methods combining MAP adaptation with the linear regression algorithms. We incorporate these adaptation algorithms into our speech synthesis system and present several subjective and objective evaluation results showing the utility and effectiveness of these algorithms in speaker adaptation for HMM-based speech synthesis.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice}
}
@inproceedings{renals2008,
  author = {Renals, Steve and Hain, Thomas and Bourlard, Hervé},
  doi = {10.1109/HSCMA.2008.4538700},
  title = {Interpretation of Multiparty Meetings: The {AMI} and {AMIDA} Projects},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=4538666&arnumber=4538700&count=68&index=33},
  booktitle = {IEEE Workshop on Hands-Free Speech Communication and Microphone Arrays, 2008. HSCMA 2008},
  pages = {115--118},
  year = {2008},
  keywords = {AMI corpus; Meetings; evaluation; speech recognition},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/renals2008.pdf},
  abstract = {The AMI and AMIDA projects are collaborative EU projects concerned with the automatic recognition and interpretation of multiparty meetings. This paper provides an overview of the advances we have made in these projects with a particular focus on the multimodal recording infrastructure, the publicly available AMI corpus of annotated meeting recordings, and the speech recognition framework that we have developed for this domain.}
}
@inproceedings{vipperla08,
  author = {Vipperla, Ravichander and Renals, Steve and Frankel, Joe},
  title = {Longitudinal study of {ASR} performance on ageing voices},
  booktitle = {Proc.~Interspeech},
  address = {Brisbane},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/vipperla_is08.pdf},
  abstract = {This paper presents the results of a longitudinal study of ASR performance on ageing voices. Experiments were conducted on the audio recordings of the proceedings of the Supreme Court Of The United States (SCOTUS). Results show that the Automatic Speech Recognition (ASR) Word Error Rates (WERs) for elderly voices are significantly higher than those of adult voices. The word error rate increases gradually as the age of the elderly speakers increase. Use of maximum likelihood linear regression (MLLR) based speaker adaptation on ageing voices improves the WER though the performance is still considerably lower compared to adult voices. Speaker adaptation however reduces the increase in WER with age during old age.}
}
@article{zhang-spl2008,
  author = {Zhang, Le and Renals, Steve},
  title = {Acoustic-Articulatory Modelling with the Trajectory {HMM}},
  journal = {IEEE Signal Processing Letters},
  pages = {245-248},
  volume = {15},
  key = {articulatory inversion},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/zhang-spl.pdf},
  abstract = {In this letter, we introduce an hidden Markov model (HMM)-based inversion system to recovery articulatory movements from speech acoustics. Trajectory HMMs are used as generative models for modelling articulatory data. Experiments on the MOCHA-TIMIT corpus indicate that the jointly trained acoustic-articulatory models are more accurate (lower RMS error) than the separately trained ones, and that trajectory HMM training results in greater accuracy compared with conventional maximum likelihood HMM training. Moreover, the system has the ability to synthesize articulatory movements directly from a textual representation.}
}
@article{treeboosting-junichi,
  author = {Yamagishi, Junichi and Kawai, Hisashi and Kobayashi, Takao},
  volume = {50},
  doi = {10.1016/j.specom.2007.12.003},
  title = {Phone Duration Modeling Using Gradient Tree Boosting},
  journal = {Speech Communication},
  number = {5},
  month = {May},
  note = {},
  pages = {405--415},
  key = {treeboosting-junichi},
  year = {2008},
  abstract = {In text-to-speech synthesis systems, phone duration influences the quality and naturalness of synthetic speech. In this study, we incorporate an ensemble learning technique called gradient tree boosting into phone duration modeling as an alternative to the conventional approach using regression trees, and objectively evaluate the prediction accuracy of Japanese, Mandarin, and English phone duration. The gradient tree boosting algorithm is a meta algorithm of regression trees: it iteratively builds the regression tree from the residuals and outputs weighting sum of the regression trees. Our evaluation results show that compared to the regression trees or other techniques related to the regression trees, the gradient tree boosting algorithm can substantially and robustly improve the predictive accuracy of the phone duration regardless of languages, speakers, or domains.},
  categories = {Text-to-speech synthesis, Phone duration modeling, Gradient tree boosing}
}
@inproceedings{ling:richmond:yamagishi:wang:2008a,
  author = {Ling, Zhen-Hua and Richmond, Korin and Yamagishi, Junichi and Wang, Ren-Hua},
  title = {Articulatory Control of {HMM}-based Parametric Speech Synthesis Driven by Phonetic Knowledge},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  pages = {573--576},
  key = {ling:richmond:yamagishi:wang:2008a},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080582.PDF},
  abstract = {This paper presents a method to control the characteristics of synthetic speech flexibly by integrating articulatory features into a Hidden Markov Model (HMM)-based parametric speech synthesis system. In contrast to model adaptation and interpolation approaches for speaking style control, this method is driven by phonetic knowledge, and target speech samples are not required. The joint distribution of parallel acoustic and articulatory features considering cross-stream feature dependency is estimated. At synthesis time, acoustic and articulatory features are generated simultaneously based on the maximum-likelihood criterion. The synthetic speech can be controlled flexibly by modifying the generated articulatory features according to arbitrary phonetic rules in the parameter generation process. Our experiments show that the proposed method is effective in both changing the overall character of synthesized speech and in controlling the quality of a specific vowel.},
  categories = {speech synthesis, HMM, articulatory features, phonetic knowledge}
}
@inproceedings{goedde:08,
  author = {G\"odde, Florian and M\"oller, Sebastian and Engelbrecht, Klaus-Peter and K\"uhnel, Christine and Schleicher, Robert and Naumann, Anja and Wolters, Maria},
  booktitle = {International Workshop on Intelligent User Interfaces for Ambient Assisted Living},
  title = {Study of a Speech-based Smart Home System with Older Users},
  pages = {17--22},
  year = {2008}
}
@inproceedings{cereproc-hts,
  author = {Aylett, Matthew P. and Yamagishi, Junichi},
  title = {Combining Statistical Parameteric Speech Synthesis and Unit-Selection for Automatic Voice Cloning},
  booktitle = {Proc. LangTech 2008},
  year = {2008},
  month = {September},
  key = {cereproc-hts},
  address = {Brisbane, Australia},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/03_AYLETT.pdf},
  abstract = {The ability to use the recorded audio of a subject's voice to produce an open-domain synthesis system has generated much interest both in academic research and in commercial speech technology. The ability to produce synthetic versions of a subjects voice has potential commercial applications, such as virtual celebrity actors, or potential clinical applications, such as offering a synthetic replacement voice in the case of a laryngectomy. Recent developments in HMM-based speech synthesis have shown it is possible to produce synthetic voices from quite small amounts of speech data. However, mimicking the depth and variation of a speaker's prosody as well as synthesising natural voice quality is still a challenging research problem. In contrast, unit-selection systems have shown it is possible to strongly retain the character of the voice but only with sufficient original source material. Often this runs into hours and may require significant manual checking and labelling. In this paper we will present two state of the art systems, an HMM based system HTS-2007, developed by CSTR and Nagoya Institute Technology, and a commercial unit-selection system CereVoice, developed by Cereproc. Both systems have been used to mimic the voice of George W. Bush (43rd president of the United States) using freely available audio from the web. In addition we will present a hybrid system which combines both technologies. We demonstrate examples of synthetic voices created from 10, 40 and 210 minutes of randomly selected speech. We will then discuss the underlying problems associated with voice cloning using found audio, and the scalability of our solution.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice}
}
@inproceedings{tietze:08:sci,
  author = {Tietze, Martin and Demberg, Vera and Moore, Johanna D.},
  title = {Syntactic Complexity induces Explicit Grounding in the {MapTask} corpus},
  booktitle = {Proc. Interspeech},
  month = {September},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS081130.pdf},
  abstract = {This paper provides evidence for theories of grounding and dialogue management in human conversation. For each utterance in a corpus of task-oriented dialogues, we calculated integration costs, which are based on syntactic sentence complexity. We compared the integration costs and grounding behavior under two conditions, namely face-to-face and a no-eye-contact condition. The results show that integration costs were significantlyhigher for explicitly grounded utterances in the no-eye-contact condition, but not in the face-to-face condition.},
  categories = {dialogue, syntactic complexity, grounding}
}
@inproceedings{bell_king_shrinkage_is2008,
  author = {Bell, Peter and King, Simon},
  title = {A Shrinkage Estimator for Speech Recognition with Full Covariance {HMM}s},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  note = {Shortlisted for best student paper award.},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/shrinkage_is2008.pdf},
  abstract = {We consider the problem of parameter estimation in full-covariance Gaussian mixture systems for automatic speech recognition. Due to the high dimensionality of the acoustic feature vector, the standard sample covariance matrix has a high variance and is often poorly-conditioned when the amount of training data is limited. We explain how the use of a shrinkage estimator can solve these problems, and derive a formula for the optimal shrinkage intensity. We present results of experiments on a phone recognition task, showing that the estimator gives a performance improvement over a standard full-covariance system}
}
@incollection{murray2008c,
  author = {Murray, Gabriel and Kleinbauer, Thomas and Poller, Peter and Renals, Steve and Kilgour, Jonathan},
  publisher = {Springer},
  doi = {10.1007/978-3-540-85853-9_32},
  title = {Extrinsic Summarization Evaluation: A Decision Audit Task},
  series = {Lecture Notes in Computer Science},
  booktitle = {Machine Learning for Multimodal Interaction (Proc. MLMI '08)},
  number = {5237},
  pages = {349--361},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/murray2008c.pdf},
  abstract = {In this work we describe a large-scale extrinsic evaluation of automatic speech summarization technologies for meeting speech. The particular task is a decision audit, wherein a user must satisfy a complex information need, navigating several meetings in order to gain an understanding of how and why a given decision was made. We compare the usefulness of extractive and abstractive technologies in satisfying this information need, and assess the impact of automatic speech recognition (ASR) errors on user performance. We employ several evaluation methods for participant performance, including post-questionnaire data, human subjective and objective judgments, and an analysis of participant browsing behaviour.}
}
@inproceedings{wang:frankel:tejedor:king:icassp2008,
  author = {Wang, Dong and Frankel, Joe and Tejedor, Javier and King, Simon},
  doi = {10.1109/ICASSP.2008.4518773},
  title = {A comparison of phone and grapheme-based spoken term detection},
  booktitle = {Proc. ICASSP},
  month = {March},
  pages = {4969--4972},
  year = {2008},
  abstract = {We propose grapheme-based sub-word units for spoken term detection (STD). Compared to phones, graphemes have a number of potential advantages. For out-of-vocabulary search terms, phone- based approaches must generate a pronunciation using letter-to-sound rules. Using graphemes obviates this potentially error-prone hard decision, shifting pronunciation modelling into the statistical models describing the observation space. In addition, long-span grapheme language models can be trained directly from large text corpora. We present experiments on Spanish and English data, comparing phone and grapheme-based STD. For Spanish, where phone and grapheme-based systems give similar transcription word error rates (WERs), grapheme-based STD significantly outperforms a phone- based approach. The converse is found for English, where the phone-based system outperforms a grapheme approach. However, we present additional analysis which suggests that phone-based STD performance levels may be achieved by a grapheme-based approach despite lower transcription accuracy, and that the two approaches may usefully be combined. We propose a number of directions for future development of these ideas, and suggest that if grapheme-based STD can match phone-based performance, the inherent flexibility in dealing with out-of-vocabulary terms makes this a desirable approach.}
}
@inproceedings{huang2008-is,
  author = {Huang, Songfang and Renals, Steve},
  title = {Unsupervised Language Model Adaptation Based on Topic and Role Information in Multiparty Meetings},
  booktitle = {Proc. Interspeech'08},
  address = {Brisbane, Australia},
  month = {September},
  pages = {833--836},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/interspeech08.pdf},
  abstract = {We continue our previous work on the modeling of topic and role information from multiparty meetings using a hierarchical Dirichlet process (HDP), in the context of language model adaptation. In this paper we focus on three problems: 1) an empirical analysis of the HDP as a nonparametric topic model; 2) the mismatch problem of vocabularies of the baseline n-gram model and the HDP; and 3) an automatic speech recognition experiment to further verify the effectiveness of our adaptation framework. Experiments on a large meeting corpus of more than 70 hours speech data show consistent and significant improvements in terms of word error rate for language model adaptation based on the topic and role information.}
}
@inproceedings{kocjancic_issp08,
  author = {Kocjancic, Tanja},
  title = {Ultrasound investigation of tongue movements in syllables with different onset structure},
  booktitle = {Proc. Eighth International Seminar on Speech Production (ISSP)},
  month = {December},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/Kocjancic_ISSP_2008.pdf},
  abstract = {This study is an attempt to describe syllables with different onset structure not only in terms of durational changes but also in terms of the distance the tongue travels over a syllable by using ultrasound and to compare the ratio between the two parameters, expressed as speed. Results indicate that both measures increase with an increasing number of onset segments but not to the same degree for all targets. Therefore speed was not constant over all of them. Additionally, type of onset constituent greatly influenced the three parameters and there were large between-speaker similarities in case of durational changes.},
  categories = {tongue movements, ultrasound}
}
@inproceedings{gibbonmayo:08,
  author = {Gibbon, F. and Mayo, C.},
  booktitle = {4th International EPG Symposium, Edinburgh, UK.},
  title = {Adults' perception of conflicting acoustic cues associated with EPG-defined undifferentiated gestures},
  categories = {speech perception, cue weighting, undifferentiated gestures, electropalatography},
  year = {2008}
}
@article{goubanova:king:specom2008,
  author = {Goubanova, Olga and King, Simon},
  doi = {10.1016/j.specom.2007.10.002},
  title = {Bayesian networks for phone duration prediction},
  journal = {Speech Communication},
  number = {4},
  month = {April},
  volume = {50},
  pages = {301-311},
  year = {2008},
  abstract = {In a text-to-speech system, the duration of each phone may be predicted by a duration model. This model is usually trained using a database of phones with known durations; each phone (and the context it appears in) is characterised by a feature vector that is composed of a set of linguistic factor values. We describe the use of a graphical model -- a Bayesian network -- for predicting the duration of a phone, given the values for these factors. The network has one discrete variable for each of the linguistic factors and a single continuous variable for the phone's duration. Dependencies between variables (or the lack of them) are represented in the BN structure by arcs (or missing arcs) between pairs of nodes. During training, both the topology of the network and its parameters are learned from labelled data. We compare the results of the BN model with results for sums of products and CART models on the same data. In terms of the root mean square error, the BN model performs much better than both CART and SoP models. In terms of correlation coefficient, the BN model performs better than the SoP model, and as well as the CART model. A BN model has certain advantages over CART and SoP models. Training SoP models requires a high degree of expertise. CART models do not deal with interactions between factors in any explicit way. As we demonstrate, a BN model can also make accurate predictions of a phone's duration, even when the values for some of the linguistic factors are unknown.},
  categories = {Text-to-speech; Bayesian networks; Duration modelling; Sums of products; Classification and regression trees}
}
@inproceedings{Aylett+King08,
  author = {Aylett, Matthew P. and King, Simon},
  title = {Single Speaker Segmentation and Inventory Selection Using Dynamic Time Warping Self Organization and Joint Multigram Mapping},
  booktitle = {SSW06},
  pages = {258--263},
  place = {Bonn},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/ssw06.pdf},
  abstract = {In speech synthesis the inventory of units is decided by inspection and on the basis of phonological and phonetic expertise. The ephone (or emergent phone) project at CSTR is investigating how self organisation techniques can be applied to build an inventory based on collected acoustic data together with the constraints of a synthesis lexicon. In this paper we will describe a prototype inventory creation method using dynamic time warping (DTW) for acoustic clustering and a joint multigram approach for relating a series of symbols that represent the speech to these emerged units. We initially examined two symbol sets: 1) A baseline of standard phones 2) Orthographic symbols. The success of the approach is evaluated by comparing word boundaries generated by the emergent phones against those created using state-of-the-art HMM segmentation. Initial results suggest the DTW segmentation can match word boundaries with a root mean square error (RMSE) of 35ms. Results from mapping units onto phones resulted in a higher RMSE of 103ms. This error was increased when multiple multigram types were added and when the default unit clustering was altered from 40 (our baseline) to 10. Results for orthographic matching had a higher RMSE of 125ms. To conclude we discuss future work that we believe can reduce this error rate to a level sufficient for the techniques to be applied to a unit selection synthesis system.},
  categories = {speech synthesis, unit selection, parametric synthesis, phone inventory, orthographic synthesis}
}
@incollection{murray2008b,
  author = {Murray, Gabriel and Renals, Steve},
  publisher = {Springer},
  doi = {10.1007/978-3-540-85853-9_19},
  title = {Detecting Action Items in Meetings},
  url = {http://dx.doi.org/10.1007/978-3-540-85853-9_19},
  series = {Lecture Notes in Computer Science},
  booktitle = {Machine Learning for Multimodal Interaction (Proc. MLMI '08)},
  number = {5237},
  pages = {208--213},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/murray2008b.pdf},
  abstract = {We present a method for detecting action items in spontaneous meeting speech. Using a supervised approach incorporating prosodic, lexical and structural features, we can classify such items with a high degree of accuracy. We also examine how well various feature subclasses can perform this task on their own.}
}
@inproceedings{robust-hts,
  author = {Yamagishi, Junichi and Ling, Zhenhua and King, Simon},
  title = {Robustness of HMM-based Speech Synthesis},
  booktitle = {Proc. Interspeech 2008},
  address = {Brisbane, Australia},
  month = {September},
  pages = {581--584},
  key = {robust-hts},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/RobustnessHTS.pdf},
  abstract = {As speech synthesis techniques become more advanced, we are able to consider building high-quality voices from data collected outside the usual highly-controlled recording studio environment. This presents new challenges that are not present in conventional text-to-speech synthesis: the available speech data are not perfectly clean, the recording conditions are not consistent, and/or the phonetic balance of the material is not ideal. Although a clear picture of the performance of various speech synthesis techniques (e.g., concatenative, HMM-based or hybrid) under good conditions is provided by the Blizzard Challenge, it is not well understood how robust these algorithms are to less favourable conditions. In this paper, we analyse the performance of several speech synthesis methods under such conditions. This is, as far as we know, a new research topic: ``Robust speech synthesis.'' As a consequence of our investigations, we propose a new robust training method for the HMM-based speech synthesis in for use with speech data collected in unfavourable conditions.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice, unit selection}
}
@inproceedings{kocjancic_exling08,
  author = {Kocjancic, Tanja},
  title = {Tongue movement and syllable onset complexity: ultrasound study},
  booktitle = {Proc. ISCA Experimental Linguistics ExLing 2008},
  month = {August},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/Kocjancic_ISCA_ExLing_2008.pdf},
  abstract = {In this study ultrasound was used to investigate tongue movements in syllables with different number and type of onset consonants. Ultrasound recordings provided the information of the distance the tongue travels over a target, and audio recordings of the time needed. The speed of tongue’s travel was calculated from the two measurements. Results of ten speakers have shown that both duration and distance travelled increase with an increased number of onset segments, but that distance travelled is additionally influenced by the type of the segment, as is speed. Duration also seemed to be the least speaker-dependant of the three parameters.},
  categories = {tongue movements, ultrasound}
}
@inproceedings{georgila:08,
  author = {Georgila, Kallirroi and Wolters, Maria and Karaiskos, Vasilis and Kronenthal, Melissa and Logie, Robert and Mayo, Neil and Moore, Johanna and Watson, Matt},
  booktitle = {Proceedings of the 6th International Conference on Language Resources and Evaluation},
  title = {A Fully Annotated Corpus for Studying the Effect of Cognitive Ageing on Users' Interactions with Spoken Dialogue Systems},
  year = {2008}
}
@article{garau2008,
  author = {Garau, Giulia and Renals, Steve},
  doi = {10.1109/TASL.2008.916519},
  title = {Combining Spectral Representations for Large Vocabulary Continuous Speech Recognition},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4443886},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  number = {3},
  pages = {508--518},
  volume = {16},
  year = {2008},
  pdf = {http://www.cstr.ed.ac.uk/downloads/publications/2008/garau-taslp08.pdf},
  abstract = {In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoustic features obtained using a pitch-synchronous analysis, STRAIGHT, in combination with conventional features such as mel frequency cepstral coefficients. Pitch-synchronous acoustic features are of particular interest when used with vocal tract length normalisation (VTLN) which is known to be affected by the fundamental frequency. We have combined these spectral representations directly at the acoustic feature level using heteroscedastic linear discriminant analysis (HLDA) and at the system level using ROVER. We evaluated this approach on three LVCSR tasks: dictated newspaper text (WSJCAM0), conversational telephone speech (CTS), and multiparty meeting transcription. The CTS and meeting transcription experiments were both evaluated using standard NIST test sets and evaluation protocols. Our results indicate that combining conventional and pitch-synchronous acoustic feature sets using HLDA results in a consistent, significant decrease in word error rate across all three tasks. Combining at the system level using ROVER resulted in a further significant decrease in word error rate.}
}
@inproceedings{qin:perpinan:richmond:wrench:renals:2008a,
  author = {Qin, C. and Carreira-Perpiñán, M. and Richmond, K. and Wrench, A. and Renals, S.},
  title = {Predicting Tongue Shapes from a Few Landmark Locations},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  pages = {2306--2309},
  key = {qin:perpinan:richmond:wrench:renals:2008a},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080929.PDF},
  abstract = {We present a method for predicting the midsagittal tongue contour from the locations of a few landmarks (metal pellets) on the tongue surface, as used in articulatory databases such as MOCHA and the Wisconsin XRDB. Our method learns a mapping using ground-truth tongue contours derived from ultrasound data and drastically improves over spline interpolation. We also determine the optimal locations of the landmarks, and the number of landmarks required to achieve a desired prediction error: 3-4 landmarks are enough to achieve 0.3-0.2 mm error per point on the tongue.},
  categories = {ultrasound, tongue contour, articulation}
}
@inproceedings{cabral:renals:richmond:yamagishi:2008a,
  author = {Cabral, J. and Renals, S. and Richmond, K. and Yamagishi, J.},
  title = {Glottal Spectral Separation for Parametric Speech Synthesis},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  pages = {1829--1832},
  key = {cabral:renals:richmond:yamagishi:2008a},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS081086.PDF},
  abstract = {This paper presents a method to control the characteristics of synthetic speech flexibly by integrating articulatory features into a Hidden Markov Model (HMM)-based parametric speech synthesis system. In contrast to model adaptation and interpolation approaches for speaking style control, this method is driven by phonetic knowledge, and target speech samples are not required. The joint distribution of parallel acoustic and articulatory features considering cross-stream feature dependency is estimated. At synthesis time, acoustic and articulatory features are generated simultaneously based on the maximum-likelihood criterion. The synthetic speech can be controlled flexibly by modifying the generated articulatory features according to arbitrary phonetic rules in the parameter generation process. Our experiments show that the proposed method is effective in both changing the overall character of synthesized speech and in controlling the quality of a specific vowel.},
  categories = {HMM speech synthesis, Glottal Spectral Separation, LF-model}
}
@inproceedings{leo_08-3,
  author = {Andersson, J. Sebastian and Badino, Leonardo and Watts, Oliver S. and P.Aylett, Matthew},
  title = {The {CSTR/Cereproc B}lizzard Entry 2008: The Inconvenient Data},
  booktitle = {Proc. Blizzard Challenge Workshop (in Proc. Interspeech 2008)},
  address = {Brisbane, Australia},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/cstr-cereproc_Blizzard2008.pdf},
  abstract = {In a commercial system data used for unit selection systems is collected with a heavy emphasis on homogeneous neutral data that has sufficient coverage for the units that will be used in the system. In this years Blizzard entry CSTR and CereProc present a joint entry where the emphasis has been to explore techniques to deal with data which is not homogeneous (the English entry) and did not have appropriate coverage for a diphone based system (the Mandarin entry where tone/phone combinations were treated as distinct phone categories). In addition, two further problems were addressed, 1) Making use of non-homogeneous data for creating a voice that can realise both expressive and neutral speaking styles (the English entry) 2) Building a unit selection system with no native understanding of the language but depending instead on external native evaluation (the Mandarin Entry).}
}
@inproceedings{hts-child-oliver,
  author = {Watts, Oliver and Yamagishi, Junichi and Berkling, Kay and King, Simon},
  title = {{HMM}-based synthesis of child speech},
  booktitle = {Proc. 1st Workshop on Child, Computer and Interaction (ICMI'08 post-conference workshop)},
  year = {2008},
  month = {October},
  key = {hts-child-oliver},
  address = {Crete, Greece},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/child-hts-oliver.pdf},
  abstract = {The synthesis of child speech presents challenges both in the collection of data and in the building of a synthesiser from that data. Because only limited data can be collected, and the domain of that data is constrained, it is difficult to obtain the type of phonetically-balanced corpus usually used in speech synthesis. As a consequence, building a synthesiser from this data is difficult. Concatenative synthesisers are not robust to corpora with many missing units (as is likely when the corpus content is not carefully designed), so we chose to build a statistical parametric synthesiser using the HMM-based system HTS. This technique has previously been shown to perform well for limited amounts of data, and for data collected under imperfect conditions. We compared 6 different configurations of the synthesiser, using both speaker-dependent and speaker-adaptive modelling techniques, and using varying amounts of data. The output from these systems was evaluated alongside natural and vocoded speech, in a Blizzard-style listening test.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice, child speech}
}
@inproceedings{strom08,
  author = {Strom, Volker and King, Simon},
  ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080514.ps},
  title = {Investigating {F}estival's target cost function using perceptual experiments},
  booktitle = {Proc.~Interspeech},
  address = {Brisbane},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080514.pdf},
  abstract = {We describe an investigation of the target cost used in the Festival unit selection speech synthesis system. Our ultimate goal is to automatically learn a perceptually optimal target cost function. In this study, we investigated the behaviour of the target cost for one segment type. The target cost is based on counting the mismatches in several context features. A carrier sentence (``My name is Roger'') was synthesised using all 147,820 possible combinations of the diphones /n_ei/ and /ei_m/. 92 representative versions were selected and presented to listeners as 460 pairwise comparisons. The listeners' preference votes were used to analyse the behaviour of the target cost, with respect to the values of its component linguistic context features.},
  categories = {speech synthesis, unit selection, target costs}
}
@inproceedings{dong_ivan_joe_simon_interspeech08_marray,
  author = {Wang, Dong and Himawan, Ivan and Frankel, Joe and King, Simon},
  title = {A Posterior Approach for Microphone Array Based Speech Recognition},
  booktitle = {Proc. Interspeech},
  month = {September},
  pages = {996--999},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/marray.a.pdf},
  abstract = {Automatic speech recognition (ASR) becomes rather difficult in meetings domains because of the adverse acoustic conditions, including more background noise, more echo and reverberation and frequent cross-talking. Microphone arrays have been demonstrated able to boost ASR performance dramatically in such noisy and reverberant environments, with various beamforming algorithms. However, almost all existing beamforming measures work in the acoustic domain, resorting to signal processing theories and geometric explanation. This limits their application, and induces significant performance degradation when the geometric property is unavailable or hard to estimate, or if heterogenous channels exist in the audio system. In this paper, we preset a new posterior-based approach for array-based speech recognition. The main idea is, instead of enhancing speech signals, we try to enhance the posterior probabilities that frames belonging to recognition units, e.g., phones. These enhanced posteriors are then transferred to posterior probability based features and are modeled by HMMs, leading to a tandem ANN-HMM hybrid system presented by Hermansky et al.. Experimental results demonstrated the validity of this posterior approach. With the posterior accumulation or enhancement, significant improvement was achieved over the single channel baseline. Moreover, we can combine the acoustic enhancement and posterior enhancement together, leading to a hybrid acoustic-posterior beamforming approach, which works significantly better than just the acoustic beamforming, especially in the scenario with moving-speakers.},
  categories = {speech recognition, microphone array, beamforming, tandem approach}
}
@article{christensen2008,
  author = {Christensen, Heidi and Gotoh, Yoshihiko and Renals, Steve},
  doi = {10.1109/TASL.2007.910746},
  title = {A Cascaded Broadcast News Highlighter},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=4407525&arnumber=4383075&count=28&index=16},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  pages = {151--161},
  volume = {16},
  year = {2008},
  pdf = {http://www.cstr.ed.ac.uk/downloads/publications/2008/christensen-tasl08.pdf},
  abstract = {This paper presents a fully automatic news skimming system which takes a broadcast news audio stream and provides the user with the segmented, structured and highlighted transcript. This constitutes a system with three different, cascading stages: converting the audio stream to text using an automatic speech recogniser, segmenting into utterances and stories and finally determining which utterance should be highlighted using a saliency score. Each stage must operate on the erroneous output from the previous stage in the system; an effect which is naturally amplified as the data progresses through the processing stages. We present a large corpus of transcribed broadcast news data enabling us to investigate to which degree information worth highlighting survives this cascading of processes. Both extrinsic and intrinsic experimental results indicate that mistakes in the story boundary detection has a strong impact on the quality of highlights, whereas erroneous utterance boundaries cause only minor problems. Further, the difference in transcription quality does not affect the overall performance greatly.}
}
@incollection{huang2008-mlmi,
  editor = {Popescu-Belis, A. and Stiefelhagen, R.},
  author = {Huang, Songfang and Renals, Steve},
  publisher = {Springer},
  title = {Modeling Topic and Role Information in Meetings using the Hierarchical {D}irichlet Process},
  series = {Lecture Notes in Computer Science},
  booktitle = {Machine Learning for Multimodal Interaction V},
  pages = {214--225},
  volume = {5237},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/mlmi08.pdf},
  abstract = {In this paper, we address the modeling of topic and role information in multiparty meetings, via a nonparametric Bayesian model called the hierarchical Dirichlet process. This model provides a powerful solution to topic modeling and a flexible framework for the incorporation of other cues such as speaker role information. We present our modeling framework for topic and role on the AMI Meeting Corpus, and illustrate the effectiveness of the approach in the context of adapting a baseline language model in a large-vocabulary automatic speech recognition system for multiparty meetings. The adapted LM produces significant improvements in terms of both perplexity and word error rate.}
}
@inproceedings{wolters-itg:08,
  author = {Wolters, Maria and Campbell, Pauline and DePlacido, Christine and Liddell, Amy and Owens, David},
  title = {Adapting {S}peech {S}ynthesis {S}ystems to {U}sers with {A}ge-{R}elated {H}earing {L}oss},
  url = {http://homepages.inf.ed.ac.uk/mwolters/itg08.pdf},
  booktitle = {Beitr{\"a}ge der 8. {ITG} {F}achtagung {S}prachkommunikation},
  month = {September},
  year = {2008},
  abstract = {This paper summarises the main results of a pilot study into the effect of auditory ageing on the intelligibility of synthetic speech. 32 older and 12 younger users had to answer simple questions about a series of meeting reminders and medication reminders. They also underwent an extensive battery of audiological and cognitive assessments. Older users only had more difficulty understanding the synthetic voice than younger people if they had elevated pure-tone thresholds and if they were asked to unfamiliar medication names. We suggest that these problems can be remedied by better prompt design. User interviews show that the synthetic voice used was quite natural. Problems mentioned by users fit the results of a previous error analysis.},
  categories = {speech synthesis, older users}
}
@inproceedings{steiner:richmond:2008a,
  author = {Steiner, I. and Richmond, K.},
  title = {Generating gestural timing from {EMA} data using articulatory resynthesis},
  booktitle = {Proc. 8th International Seminar on Speech Production},
  year = {2008},
  month = {December},
  key = {steiner:richmond:2008a},
  address = {Strasbourg, France},
  abstract = {As part of ongoing work to integrate an articulatory synthesizer into a modular TTS platform, a method is presented which allows gestural timings to be generated automatically from EMA data. Further work is outlined which will adapt the vocal tract model and phoneset to English using new articulatory data, and use statistical trajectory models.},
  categories = {articulatory synthesis, EMA, VocalTractLab}
}
@inproceedings{leo_08-2,
  author = {Badino, Leonardo and Clark, Robert A.J. and Strom, Volker},
  ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080159.ps},
  title = {Including Pitch Accent Optionality in Unit Selection Text-to-Speech Synthesis},
  booktitle = {Proc.~Interspeech},
  address = {Brisbane},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080159.pdf},
  abstract = {A significant variability in pitch accent placement is found when comparing the patterns of prosodic prominence realized by different English speakers reading the same sentences. In this paper we describe a simple approach to incorporate this variability to synthesize prosodic prominence in unit selection text-to-speech synthesis. The main motivation of our approach is that by taking into account the variability of accent placements we enlarge the set of prosodically acceptable speech units, thus increasing the chances of selecting a good quality sequence of units, both in prosodic and segmental terms. Results on a large scale perceptual test show the benefits of our approach and indicate directions for further improvements.},
  categories = {speech synthesis, unit selection, prosodic prominence, pitch accents}
}
@inproceedings{joe_dong_simon_interspeech08_bottle,
  author = {Frankel, Joe and Wang, Dong and King, Simon},
  title = {Growing bottleneck features for tandem {ASR}},
  booktitle = {Proc. Interspeech},
  month = {September},
  pages = {1549},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/bottlenet.a.pdf},
  abstract = {We present a method for training bottleneck MLPs for use in tandem ASR. Experiments on meetings data show that this approach leads to improved performance compared with training MLPs from a random initialization.},
  categories = {tandem ASR, bottleneck MLP}
}
@inproceedings{tts_barra08,
  author = {Barra-Chicote, R. and Yamagishi, J. and Montero, J.M. and King, S. and Lutfi, S. and Macias-Guarasa, J.},
  title = {Generacion de una voz sintetica en {C}astellano basada en {HSMM} para la {E}valuacion {A}lbayzin 2008: conversion texto a voz},
  booktitle = {V Jornadas en Tecnologia del Habla},
  month = {November},
  note = {(in Spanish)},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/tts-jth08.pdf},
  pages = {115-118}
}
@inproceedings{lips08-gregpr,
  author = {Hofer, Gregor and Yamagishi, Junichi and Shimodaira, Hiroshi},
  title = {Speech-driven Lip Motion Generation with a Trajectory {HMM}},
  booktitle = {Proc. Interspeech 2008},
  address = {Brisbane, Australia},
  month = {September},
  pages = {2314--2317},
  key = {lips08-gregpr},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/GregorLipsChallenge08.pdf},
  abstract = {Automatic speech animation remains a challenging problem that can be described as finding the optimal sequence of animation parameter configurations given some speech. In this paper we present a novel technique to automatically synthesise lip motion trajectories from a speech signal. The developed system predicts lip motion units from the speech signal and generates animation trajectories automatically employing a "Trajectory Hidden Markov Model". Using the MLE criterion, its parameter generation algorithm produces the optimal smooth motion trajectories that are used to drive control points on the lips directly. Additionally, experiments were carried out to find a suitable model unit that produces the most accurate results. Finally a perceptual evaluation was conducted, that showed that the developed motion units perform better than phonemes.},
  categories = {visual speech synthesis, trajectory HMM, HTS}
}
@incollection{murray2008a,
  author = {Murray, Gabriel and Renals, Steve},
  publisher = {Springer},
  doi = {10.1007/978-3-540-85853-9_22},
  title = {Meta Comments for Summarizing Meeting Speech},
  url = {http://dx.doi.org/10.1007/978-3-540-85853-9_22},
  series = {Lecture Notes in Computer Science},
  booktitle = {Machine Learning for Multimodal Interaction (Proc. MLMI '08)},
  number = {5237},
  pages = {236--247},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/murray2008a.pdf},
  abstract = {This paper is about the extractive summarization of meeting speech, using the ICSI and AMI corpora. In the first set of experiments we use prosodic, lexical, structural and speaker-related features to select the most informative dialogue acts from each meeting, with the hypothesis being that such a rich mixture of features will yield the best results. In the second part, we present an approach in which the identification of ``meta-comments'' is used to create more informative summaries that provide an increased level of abstraction. We find that the inclusion of these meta comments improves summarization performance according to several evaluation metrics.}
}
@inproceedings{moeller:08,
  author = {M\"oller, Sebastian and G\"odde, Florian and Wolters, Maria},
  booktitle = {Proceedings of the 6th International Conference on Language Resources and Evaluation},
  title = {A Corpus Analysis of Spoken Smart-Home Interactions with Older Users},
  year = {2008}
}
@inproceedings{king:tokuda:zen:yamagishi:interspeech2008,
  author = {King, Simon and Tokuda, Keiichi and Zen, Heiga and Yamagishi, Junichi},
  title = {Unsupervised adaptation for HMM-based speech synthesis},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  pages = {1869-1872},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080299.PDF},
  abstract = {It is now possible to synthesise speech using HMMs with a comparable quality to unit-selection techniques. Generating speech from a model has many potential advantages over concatenating waveforms. The most exciting is model adaptation. It has been shown that supervised speaker adaptation can yield high-quality synthetic voices with an order of magnitude less data than required to train a speaker-dependent model or to build a basic unit-selection system. Such supervised methods require labelled adaptation data for the target speaker. In this paper, we introduce a method capable of unsupervised adaptation, using only speech from the target speaker without any labelling.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, trajectory HMMs, speaker adaptation, MLLR}
}
@inproceedings{toth:frankel:goztolya:king:interspeech2008,
  author = {Toth, Laszlo and Frankel, Joe and Gosztolya, Gabor and King, Simon},
  title = {Cross-lingual Portability of MLP-Based Tandem Features -- A Case Study for English and Hungarian},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  pages = {2695-2698},
  year = {2008},
  keywords = {tandem, ASR},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080729.PDF},
  abstract = {One promising approach for building ASR systems for less-resourced languages is cross-lingual adaptation. Tandem ASR is particularly well suited to such adaptation, as it includes two cascaded modelling steps: feature extraction using multi-layer perceptrons (MLPs), followed by modelling using a standard HMM. The language-specific tuning can be performed by adjusting the HMM only, leaving the MLP untouched. Here we examine the portability of feature extractor MLPs between an Indo-European (English) and a Finno-Ugric (Hungarian) language. We present experiments which use both conventional phone-posterior and articulatory feature (AF) detector MLPs, both trained on a much larger quantity of (English) data than the monolingual (Hungarian) system. We find that the cross-lingual configurations achieve similar performance to the monolingual system, and that, interestingly, the AF detectors lead to slightly worse performance, despite the expectation that they should be more language-independent than phone-based MLPs. However, the cross-lingual system outperforms all other configurations when the English phone MLP is adapted on the Hungarian data.}
}
@inproceedings{garau2008a,
  author = {Garau, Giulia and Renals, Steve},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/garau2008a.pdf},
  booktitle = {Proc. Interspeech '08},
  title = {Pitch adaptive features for {LVCSR}},
  abstract = {We have investigated the use of a pitch adaptive spectral representation on large vocabulary speech recognition, in conjunction with speaker normalisation techniques. We have compared the effect of a smoothed spectrogram to the pitch adaptive spectral analysis by decoupling these two components of STRAIGHT. Experiments performed on a large vocabulary meeting speech recognition task highlight the importance of combining a pitch adaptive spectral representation with a conventional fixed window spectral analysis. We found evidence that STRAIGHT pitch adaptive features are more speaker independent than conventional MFCCs without pitch adaptation, thus they also provide better performances when combined using feature combination techniques such as Heteroscedastic Linear Discriminant Analysis.},
  year = {2008}
}
@article{tejedor:wang:frankel:king:colas:specom2008,
  author = {Tejedor, Javier and Wang, Dong and Frankel, Joe and King, Simon and Colás, José},
  doi = {10.1016/j.specom.2008.03.005},
  title = {A comparison of grapheme and phoneme-based units for {S}panish spoken term detection},
  journal = {Speech Communication},
  number = {11-12},
  month = {November},
  volume = {50},
  pages = {980-991},
  year = {2008},
  abstract = {The ever-increasing volume of audio data available online through the world wide web means that automatic methods for indexing and search are becoming essential. Hidden Markov model (HMM) keyword spotting and lattice search techniques are the two most common approaches used by such systems. In keyword spotting, models or templates are defined for each search term prior to accessing the speech and used to find matches. Lattice search (referred to as spoken term detection), uses a pre-indexing of speech data in terms of word or sub-word units, which can then quickly be searched for arbitrary terms without referring to the original audio. In both cases, the search term can be modelled in terms of sub-word units, typically phonemes. For in-vocabulary words (i.e. words that appear in the pronunciation dictionary), the letter-to-sound conversion systems are accepted to work well. However, for out-of-vocabulary (OOV) search terms, letter-to-sound conversion must be used to generate a pronunciation for the search term. This is usually a hard decision (i.e. not probabilistic and with no possibility of backtracking), and errors introduced at this step are difficult to recover from. We therefore propose the direct use of graphemes (i.e., letter-based sub-word units) for acoustic modelling. This is expected to work particularly well in languages such as Spanish, where despite the letter-to-sound mapping being very regular, the correspondence is not one-to-one, and there will be benefits from avoiding hard decisions at early stages of processing. In this article, we compare three approaches for Spanish keyword spotting or spoken term detection, and within each of these we compare acoustic modelling based on phone and grapheme units. Experiments were performed using the Spanish geographical-domain Albayzin corpus. Results achieved in the two approaches proposed for spoken term detection show us that trigrapheme units for acoustic modelling match or exceed the performance of phone-based acoustic models. In the method proposed for keyword spotting, the results achieved with each acoustic model are very similar.},
  categories = {Spoken term detection; Keyword spotting; Graphemes; Spanish}
}
@inproceedings{morgan:08,
  author = {Morgan, Maggie and McGee-Lennon, Marilyn R. and Hine, Nick and Arnott, John and Martin, Chris and Clark, Julia S. and Wolters, Maria},
  booktitle = {Proc. 26th Conference on Computer-Human Interaction, Florence},
  title = {Requirements Gathering with Diverse User Groups and Stakeholders},
  year = {2008}
}
@inproceedings{hts2007-icassp,
  author = {Yamagishi, Junichi and Nose, Takashi and Zen, Heiga and Toda, Tomoki and Tokuda, Keiichi},
  doi = {10.1109/ICASSP.2008.4518520},
  title = {Performance Evaluation of The Speaker-Independent {HMM}-based Speech Synthesis System "{HTS}-2007" for the {Blizzard Challenge 2007}},
  booktitle = {Proc. ICASSP 2008},
  address = {Las Vegas, U.S.A},
  month = {April},
  pages = {3957--3960},
  key = {hts2007-icassp},
  year = {2008},
  abstract = {This paper describes a speaker-independent/adaptive HMM-based speech synthesis system developed for the Blizzard Challenge 2007. The new system, named "HTS-2007", employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than that of speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice}
}
@inproceedings{karaiskos:king:clark:mayo:blizzard2008,
  author = {Karaiskos, Vasilis and King, Simon and Clark, Robert A. J. and Mayo, Catherine},
  title = {The Blizzard Challenge 2008},
  booktitle = {Proc. Blizzard Challenge Workshop},
  address = {Brisbane, Australia},
  month = {September},
  year = {2008},
  keywords = {Blizzard},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/summary_Blizzard2008.pdf},
  abstract = {The Blizzard Challenge 2008 was the fourth annual Blizzard Challenge. This year, participants were asked to build two voices from a UK English corpus and one voice from a Man- darin Chinese corpus. This is the first time that a language other than English has been included and also the first time that a large UK English corpus has been available. In addi- tion, the English corpus contained somewhat more expressive speech than that found in corpora used in previous Blizzard Challenges. To assist participants with limited resources or limited ex- perience in UK-accented English or Mandarin, unaligned la- bels were provided for both corpora and for the test sentences. Participants could use the provided labels or create their own. An accent-specific pronunciation dictionary was also available for the English speaker. A set of test sentences was released to participants, who were given a limited time in which to synthesise them and submit the synthetic speech. An online listening test was con- ducted, to evaluate naturalness, intelligibility and degree of similarity to the original speaker.}
}
@inproceedings{huang2008-ptkl,
  author = {Huang, Songfang and Renals, Steve},
  title = {Using Participant Role in Multiparty Meetings as Prior Knowledge for Nonparametric Topic Modeling},
  booktitle = {Proc. ICML/UAI/COLT Workshop on Prior Knowledge for Text and Language Processing},
  address = {Helsinki, Finland},
  month = {July},
  pages = {21--24},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/ptkl.pdf},
  abstract = {In this paper we introduce our attempts to incorporate the participant role information in multiparty meetings for document modeling using the hierarchical Dirichlet process. The perplexity and automatic speech recognition results demonstrate that the participant role information is a promising prior knowledge source to be combined with language models for automatic speech recognition and interaction modeling for multiparty meetings.}
}
@inproceedings{hts2008,
  author = {Yamagishi, Junichi and Zen, Heiga and Wu, Yi-Jian and Toda, Tomoki and Tokuda, Keiichi},
  title = {The {HTS}-2008 System: Yet Another Evaluation of the Speaker-Adaptive {HMM}-based Speech Synthesis System in The {2008 Blizzard Challenge}},
  booktitle = {Proc. Blizzard Challenge 2008},
  year = {2008},
  month = {September},
  key = {hts2008},
  address = {Brisbane, Australia},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/HTS2008.pdf},
  abstract = {For the 2008 Blizzard Challenge, we used the same speaker-adaptive approach to HMM-based speech synthesis that was used in the HTS entry to the 2007 challenge, but an improved system was built in which the multi-accented English average voice model was trained on 41 hours of speech data with high-order mel-cepstral analysis using an efficient forward-backward algorithm for the HSMM. The listener evaluation scores for the synthetic speech generated from this system was much better than in 2007: the system had the equal best naturalness on the small English data set and the equal best intelligibility on both small and large data sets for English, and had the equal best naturalness on the Mandarin data. In fact, the English system was found to be as intelligible as human speech.},
  categories = {speech synthesis, HMM-based speech synthesis, HTS, speaker adaptation, voice conversion, average voice, Blizzard Challenge}
}
@inproceedings{bell_king_lineSearch_is2008,
  author = {Bell, Peter and King, Simon},
  title = {Covariance Updates for Discriminative Training by Constrained Line Search},
  booktitle = {Proc. Interspeech},
  address = {Brisbane, Australia},
  month = {September},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/lineSearch_is2008.pdf},
  abstract = {We investigate the recent Constrained Line Search algorithm for discriminative training of HMMs and propose an alternative formula for variance update. We compare the method to standard techniques on a phone recognition task.}
}
@inproceedings{leo_08-1,
  author = {Badino, Leonardo and Clark, Robert A.J.},
  title = {Automatic labeling of contrastive word pairs from spontaneous spoken English},
  booktitle = {in 2008 IEEE/ACL Workshop on Spoken Language Technology},
  address = {Goa, India},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/0000101.pdf},
  abstract = {This paper addresses the problem of automatically labeling contrast in spontaneous spoken speech, where contrast here is meant as a relation that ties two words that explicitly contrast with each other. Detection of contrast is certainly relevant in the analysis of discourse and information structure and also, because of the prosodic correlates of contrast, could play an important role in speech applications, such as text-to-speech synthesis, that need an accurate and discourse context related modeling of prosody. With this prospect we investigate the feasibility of automatic contrast labeling by training and evaluating on the Switchboard corpus a novel contrast tagger, based on Support Vector Machines (SVM), that combines lexical features, syntactic dependencies and WordNet semantic relations.}
}
@article{dielmann2008,
  author = {Dielmann, Alfred and Renals, Steve},
  doi = {10.1109/TASL.2008.922463},
  title = {Recognition of Dialogue Acts in Multiparty Meetings using a Switching {DBN}},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=4599391&arnumber=4497831&count=18&index=9},
  journal = {IEEE Transactions on Audio, Speech and Language Processing},
  number = {7},
  pages = {1303--1314},
  volume = {16},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/dielmann2008.pdf},
  abstract = {This paper is concerned with the automatic recognition of dialogue acts (DAs) in multiparty conversational speech. We present a joint generative model for DA recognition in which segmentation and classification of DAs are carried out in parallel. Our approach to DA recognition is based on a switching dynamic Bayesian network (DBN) architecture. This generative approach models a set of features, related to lexical content and prosody, and incorporates a weighted interpolated factored language model. The switching DBN coordinates the recognition process by integrating the component models. The factored language model, which is estimated from multiple conversational data corpora, is used in conjunction with additional task-specific language models. In conjunction with this joint generative model, we have also investigated the use of a discriminative approach, based on conditional random fields, to perform a reclassification of the segmented DAs. We have carried out experiments on the AMI corpus of multimodal meeting recordings, using both manually transcribed speech, and the output of an automatic speech recognizer, and using different configurations of the generative model. Our results indicate that the system performs well both on reference and fully automatic transcriptions. A further significant improvement in recognition accuracy is obtained by the application of the discriminative reranking approach based on conditional random fields.}
}
@inproceedings{bourlard2008,
  author = {Bourlard, Herve and Renals, Steve},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/bourlard2008.pdf},
  booktitle = {Proc. LangTech 2008},
  title = {Recognition and Understanding of Meetings: Overview of the {European} {AMI} and {AMIDA} Projects},
  abstract = {The AMI and AMIDA projects are concerned with the recognition and interpretation of multiparty (face-to-face and remote) meetings. Within these projects we have developed the following: (1) an infrastructure for recording meetings using multiple microphones and cameras; (2) a one hundred hour, manually annotated meeting corpus; (3) a number of techniques for indexing, and summarizing of meeting videos using automatic speech recognition and computer vision, and (4) a extensible framework for browsing, and searching of meeting videos. We give an overview of the various techniques developed in AMI (mainly involving face-to-face meetings), their integration into our meeting browser framework, and future plans for AMIDA (Augmented Multiparty Interaction with Distant Access), the follow-up project to AMI. Technical and business information related to these two projects can be found at www.amiproject.org, respectively on the Scientific and Business portals.},
  year = {2008}
}
@inproceedings{besacier2008LIG,
  author = {Besacier, Laurent and Ben Youssef, Atef and Blanchon, Hervé},
  title = {The LIG Arabic/English Speech Translation System at IWSLT08},
  booktitle = {International Workshop on Spoken Language Translation (IWSLT) 2008},
  address = {Hawaii, USA},
  pages = {58--62},
  year = {2008},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/Besacier-etal_IWSLT-2008.pdf},
  abstract = {This paper is a description of the system presented by the LIG laboratory to the IWSLT08 speech translation evaluation. The LIG participated, for the second time this year, in the Arabic to English speech translation task. For translation, we used a conventional statistical phrase-based system developed using the moses open source decoder. We describe chronologically the improvements made since last year, starting from the IWSLT 2007 system, following with the improvements made for our 2008 submission. Then, we discuss in section 5 some post-evaluation experiments made very recently, as well as some on-going work on Arabic / English speech to text translation. This year, the systems were ranked according to the (BLEU+METEOR)/2 score of the primary ASR output run submissions. The LIG was ranked 5th/10 based on this rule.}
}