The Centre for Speech Technology Research, The university of Edinburgh

Publications by Joe Frankel

[1] Dong Wang, Javier Tejedor, Simon King, and Joe Frankel. Term-dependent confidence normalization for out-of-vocabulary spoken term detection. Journal of Computer Science and Technology, 27(2), 2012. [ bib | DOI ]
Spoken Term Detection (STD) is a fundamental component of spoken information retrieval systems. A key task of an STD system is to determine reliable detections and reject false alarms based on certain confidence measures. The detection posterior probability, which is often computed from lattices, is a widely used confidence measure. However, a potential problem of this confidence measure is that the confidence scores of detections of all search terms are treated uniformly, regardless of how much they may differ in terms of phonetic or linguistic properties. This problem is particularly evident for out-of-vocabulary (OOV) terms which tend to exhibit high intra-term diversity. To address the discrepancy on confidence levels that the same confidence score may convey for different terms, a term-dependent decision strategy is desirable - for example, the term-specific threshold (TST) approach. In this work, we propose a term-dependent normalisation technique which compensates for term diversity on confidence estimation. Particularly, we propose a linear bias compensation and a discriminative compensation to deal with the bias problem that is inherent in lattice-based confidence measuring from which the TST approach suffers. We tested the proposed technique on speech data from the multi-party meeting domain with two state-of-the-art STD systems based on phonemes and words respectively. The experimental results demonstrate that the confidence normalisation approach leads to a significant performance improvement in STD, particularly for OOV terms with phoneme-based systems.

[2] Ravi Chander Vipperla, Steve Renals, and Joe Frankel. Augmentation of adaptation data. In Proc. Interspeech, pages 530-533, Makuhari, Japan, September 2010. [ bib | .pdf ]
Linear regression based speaker adaptation approaches can improve Automatic Speech Recognition (ASR) accuracy significantly for a target speaker. However, when the available adaptation data is limited to a few seconds, the accuracy of the speaker adapted models is often worse compared with speaker independent models. In this paper, we propose an approach to select a set of reference speakers acoustically close to the target speaker whose data can be used to augment the adaptation data. To determine the acoustic similarity of two speakers, we propose a distance metric based on transforming sample points in the acoustic space with the regression matrices of the two speakers. We show the validity of this approach through a speaker identification task. ASR results on SCOTUS and AMI corpora with limited adaptation data of 10 to 15 seconds augmented by data from selected reference speakers show a significant improvement in Word Error Rate over speaker independent and speaker adapted models.

[3] D. Wang, S. King, and J. Frankel. Stochastic pronunciation modelling for out-of-vocabulary spoken term detection. Audio, Speech, and Language Processing, IEEE Transactions on, PP(99), July 2010. [ bib | DOI ]
Spoken term detection (STD) is the name given to the task of searching large amounts of audio for occurrences of spoken terms, which are typically single words or short phrases. One reason that STD is a hard task is that search terms tend to contain a disproportionate number of out-of-vocabulary (OOV) words. The most common approach to STD uses subword units. This, in conjunction with some method for predicting pronunciations of OOVs from their written form, enables the detection of OOV terms but performance is considerably worse than for in-vocabulary terms. This performance differential can be largely attributed to the special properties of OOVs. One such property is the high degree of uncertainty in the pronunciation of OOVs. We present a stochastic pronunciation model (SPM) which explicitly deals with this uncertainty. The key insight is to search for all possible pronunciations when detecting an OOV term, explicitly capturing the uncertainty in pronunciation. This requires a probabilistic model of pronunciation, able to estimate a distribution over all possible pronunciations. We use a joint-multigram model (JMM) for this and compare the JMM-based SPM with the conventional soft match approach. Experiments using speech from the meetings domain demonstrate that the SPM performs better than soft match in most operating regions, especially at low false alarm probabilities. Furthermore, SPM and soft match are found to be complementary: their combination provides further performance gains.

[4] Dong Wang, Simon King, Joe Frankel, and Peter Bell. Stochastic pronunciation modelling and soft match for out-of-vocabulary spoken term detection. In Proc. ICASSP, Dallas, Texas, USA, March 2010. [ bib | .pdf ]
A major challenge faced by a spoken term detection (STD) system is the detection of out-of-vocabulary (OOV) terms. Although a subword-based STD system is able to detect OOV terms, performance reduction is always observed compared to in-vocabulary terms. One challenge that OOV terms bring to STD is the pronunciation uncertainty. A commonly used approach to address this problem is a soft matching procedure,and the other is the stochastic pronunciation modelling (SPM) proposed by the authors. In this paper we compare these two approaches, and combine them using a discriminative decision strategy. Experimental results demonstrated that SPM and soft match are highly complementary, and their combination gives significant performance improvement to OOV term detection.

Keywords: confidence estimation, spoken term detection, speech recognition
[5] Ravi Chander Vipperla, Steve Renals, and Joe Frankel. Ageing voices: The effect of changes in voice parameters on ASR performance. EURASIP Journal on Audio, Speech, and Music Processing, 2010. [ bib | DOI | http | .pdf ]
With ageing, human voices undergo several changes which are typically characterized by increased hoarseness and changes in articulation patterns. In this study, we have examined the effect on Automatic Speech Recognition (ASR) and found that the Word Error Rates (WER) on older voices is about 9% absolute higher compared to those of adult voices. Subsequently, we compared several voice source parameters including fundamental frequency, jitter, shimmer, harmonicity and cepstral peak prominence of adult and older males. Several of these parameters show statistically significant difference for the two groups. However, artificially increasing jitter and shimmer measures do not effect the ASR accuracies significantly. Artificially lowering the fundamental frequency degrades the ASR performance marginally but this drop in performance can be overcome to some extent using Vocal Tract Length Normalisation (VTLN). Overall, we observe that the changes in the voice source parameters do not have a significant impact on ASR performance. Comparison of the likelihood scores of all the phonemes for the two age groups show that there is a systematic mismatch in the acoustic space of the two age groups. Comparison of the phoneme recognition rates show that mid vowels, nasals and phonemes that depend on the ability to create constrictions with tongue tip for articulation are more affected by ageing than other phonemes.

[6] Dong Wang, Simon King, and Joe Frankel. Stochastic pronunciation modelling for spoken term detection. In Proc. Interspeech, pages 2135-2138, Brighton, UK, September 2009. [ bib | .pdf ]
A major challenge faced by a spoken term detection (STD) system is the detection of out-of-vocabulary (OOV) terms. Although a subword-based STD system is able to detect OOV terms, performance reduction is always observed compared to in-vocabulary terms. Current approaches to STD do not acknowledge the particular properties of OOV terms, such as pronunciation uncertainty. In this paper, we use a stochastic pronunciation model to deal with the uncertain pronunciations of OOV terms. By considering all possible term pronunciations, predicted by a joint-multigram model, we observe a significant performance improvement.

[7] Dong Wang, Simon King, Joe Frankel, and Peter Bell. Term-dependent confidence for out-of-vocabulary term detection. In Proc. Interspeech, pages 2139-2142, Brighton, UK, September 2009. [ bib | .pdf ]
Within a spoken term detection (STD) system, the decision maker plays an important role in retrieving reliable detections. Most of the state-of-the-art STD systems make decisions based on a confidence measure that is term-independent, which poses a serious problem for out-of-vocabulary (OOV) term detection. In this paper, we study a term-dependent confidence measure based on confidence normalisation and discriminative modelling, particularly focusing on its remarkable effectiveness for detecting OOV terms. Experimental results indicate that the term-dependent confidence provides much more significant improvement for OOV terms than terms in-vocabulary.

[8] Javier Tejedor, Dong Wang, Simon King, Joe Frankel, and Jose Colas. A posterior probability-based system hybridisation and combination for spoken term detection. In Proc. Interspeech, pages 2131-2134, Brighton, UK, September 2009. [ bib | .pdf ]
Spoken term detection (STD) is a fundamental task for multimedia information retrieval. To improve the detection performance, we have presented a direct posterior-based confidence measure generated from a neural network. In this paper, we propose a detection-independent confidence estimation based on the direct posterior confidence measure, in which the decision making is totally separated from the term detection. Based on this idea, we first present a hybrid system which conducts the term detection and confidence estimation based on different sub-word units, and then propose a combination method which merges detections from heterogeneous term detectors based on the direct posterior-based confidence. Experimental results demonstrated that the proposed methods improved system performance considerably for both English and Spanish.

[9] Dong Wang, Tejedor Tejedor, Joe Frankel, and Simon King. Posterior-based confidence measures for spoken term detection. In Proc. ICASSP09, Taiwan, April 2009. [ bib | .pdf ]
Confidence measures play a key role in spoken term detection (STD) tasks. The confidence measure expresses the posterior probability of the search term appearing in the detection period, given the speech. Traditional approaches are based on the acoustic and language model scores for candidate detections found using automatic speech recognition, with Bayes' rule being used to compute the desired posterior probability. In this paper, we present a novel direct posterior-based confidence measure which, instead of resorting to the Bayesian formula, calculates posterior probabilities from a multi-layer perceptron (MLP) directly. Compared with traditional Bayesian-based methods, the direct-posterior approach is conceptually and mathematically simpler. Moreover, the MLP-based model does not require assumptions to be made about the acoustic features such as their statistical distribution and the independence of static and dynamic co-efficients. Our experimental results in both English and Spanish demonstrate that the proposed direct posterior-based confidence improves STD performance.

[10] Javier Tejedor, Dong Wang, Joe Frankel, Simon King, and José Colás. A comparison of grapheme and phoneme-based units for Spanish spoken term detection. Speech Communication, 50(11-12):980-991, November 2008. [ bib | DOI ]
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.

[11] Dong Wang, Ivan Himawan, Joe Frankel, and Simon King. A posterior approach for microphone array based speech recognition. In Proc. Interspeech, pages 996-999, September 2008. [ bib | .pdf ]
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.

[12] Joe Frankel, Dong Wang, and Simon King. Growing bottleneck features for tandem ASR. In Proc. Interspeech, page 1549, September 2008. [ bib | .pdf ]
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.

[13] Laszlo Toth, Joe Frankel, Gabor Gosztolya, and Simon King. Cross-lingual portability of mlp-based tandem features - a case study for english and hungarian. In Proc. Interspeech, pages 2695-2698, Brisbane, Australia, September 2008. [ bib | .PDF ]
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.

Keywords: tandem, ASR
[14] Dong Wang, Joe Frankel, Javier Tejedor, and Simon King. A comparison of phone and grapheme-based spoken term detection. In Proc. ICASSP, pages 4969-4972, March 2008. [ bib | DOI ]
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.

[15] Ravichander Vipperla, Steve Renals, and Joe Frankel. Longitudinal study of ASR performance on ageing voices. In Proc. Interspeech, Brisbane, 2008. [ bib | .pdf ]
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.

[16] J. Frankel and S. King. Factoring Gaussian precision matrices for linear dynamic models. Pattern Recognition Letters, 28(16):2264-2272, December 2007. [ bib | DOI | .pdf ]
The linear dynamic model (LDM), also known as the Kalman filter model, has been the subject of research in the engineering, control, and more recently, machine learning and speech technology communities. The Gaussian noise processes are usually assumed to have diagonal, or occasionally full, covariance matrices. A number of recent papers have considered modelling the precision rather than covariance matrix of a Gaussian distribution, and this work applies such ideas to the LDM. A Gaussian precision matrix P can be factored into the form P = UTSU where U is a transform and S a diagonal matrix. By varying the form of U, the covariance can be specified as being diagonal or full, or used to model a given set of spatial dependencies. Furthermore, the transform and scaling components can be shared between models, allowing richer distributions with only marginally more parameters than required to specify diagonal covariances. The method described in this paper allows the construction of models with an appropriate number of parameters for the amount of available training data. We provide illustrative experimental results on synthetic and real speech data in which models with factored precision matrices and automatically-selected numbers of parameters are as good as or better than models with diagonal covariances on small data sets and as good as models with full covariance matrices on larger data sets.

[17] Ö. Çetin, M. Magimai-Doss, A. Kantor, S. King, C. Bartels, J. Frankel, and K. Livescu. Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPs. In Proc. ASRU, Kyoto, December 2007. IEEE. [ bib | .pdf ]
In recent years, the features derived from posteriors of a multilayer perceptron (MLP), known as tandem features, have proven to be very effective for automatic speech recognition. Most tandem features to date have relied on MLPs trained for phone classification. We recently showed on a relatively small data set that MLPs trained for articulatory feature classification can be equally effective. In this paper, we provide a similar comparison using MLPs trained on a much larger data set - 2000 hours of English conversational telephone speech. We also explore how portable phone- and articulatory feature- based tandem features are in an entirely different language - Mandarin - without any retraining. We find that while phone-based features perform slightly better in the matched-language condition, they perform significantly better in the cross-language condition. Yet, in the cross-language condition, neither approach is as effective as the tandem features extracted from an MLP trained on a relatively small amount of in-domain data. Beyond feature concatenation, we also explore novel observation modelling schemes that allow for greater flexibility in combining the tandem and standard features at hidden Markov model (HMM) outputs.

[18] J. Frankel, M. Wester, and S. King. Articulatory feature recognition using dynamic Bayesian networks. Computer Speech & Language, 21(4):620-640, October 2007. [ bib | .pdf ]
We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended to be a component of a speech recognizer that avoids the problems of conventional “beads-on-a-string” phoneme-based models. We demonstrate that the model gives superior recognition of articulatory features from the speech signal compared with a stateof- the art neural network system. We also introduce a training algorithm that offers two major advances: it does not require time-aligned feature labels and it allows the model to learn a set of asynchronous feature changes in a data-driven manner.

[19] J. Frankel, M. Magimai-Doss, S. King, K. Livescu, and Ö. Çetin. Articulatory feature classifiers trained on 2000 hours of telephone speech. In Proc. Interspeech, Antwerp, Belgium, August 2007. [ bib | .pdf ]
This paper is intended to advertise the public availability of the articulatory feature (AF) classification multi-layer perceptrons (MLPs) which were used in the Johns Hopkins 2006 summer workshop. We describe the design choices, data preparation, AF label generation, and the training of MLPs for feature classification on close to 2000 hours of telephone speech. In addition, we present some analysis of the MLPs in terms of classification accuracy and confusions along with a brief summary of the results obtained during the workshop using the MLPs. We invite interested parties to make use of these MLPs.

[20] Ö. Çetin, A. Kantor, S. King, C. Bartels, M. Magimai-Doss, J. Frankel, and K. Livescu. An articulatory feature-based tandem approach and factored observation modeling. In Proc. ICASSP, Honolulu, April 2007. [ bib | .pdf ]
The so-called tandem approach, where the posteriors of a multilayer perceptron (MLP) classifier are used as features in an automatic speech recognition (ASR) system has proven to be a very effective method. Most tandem approaches up to date have relied on MLPs trained for phone classification, and appended the posterior features to some standard feature hidden Markov model (HMM). In this paper, we develop an alternative tandem approach based on MLPs trained for articulatory feature (AF) classification. We also develop a factored observation model for characterizing the posterior and standard features at the HMM outputs, allowing for separate hidden mixture and state-tying structures for each factor. In experiments on a subset of Switchboard, we show that the AFbased tandem approach is as effective as the phone-based approach, and that the factored observation model significantly outperforms the simple feature concatenation approach while using fewer parameters.

[21] K. Livescu, Ö. Çetin, M. Hasegawa-Johnson, S. King, C. Bartels, N. Borges, A. Kantor, P. Lal, L. Yung, S. Bezman, Dawson-Haggerty, B. Woods, J. Frankel, M. Magimai-Doss, and K. Saenko. Articulatory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU Summer Workshop. In Proc. ICASSP, Honolulu, April 2007. [ bib | .pdf ]
We report on investigations, conducted at the 2006 Johns HopkinsWorkshop, into the use of articulatory features (AFs) for observation and pronunciation models in speech recognition. In the area of observation modeling, we use the outputs of AF classiers both directly, in an extension of hybrid HMM/neural network models, and as part of the observation vector, an extension of the tandem approach. In the area of pronunciation modeling, we investigate a model having multiple streams of AF states with soft synchrony constraints, for both audio-only and audio-visual recognition. The models are implemented as dynamic Bayesian networks, and tested on tasks from the Small-Vocabulary Switchboard (SVitchboard) corpus and the CUAVE audio-visual digits corpus. Finally, we analyze AF classication and forced alignment using a newly collected set of feature-level manual transcriptions.

[22] K. Livescu, A. Bezman, N. Borges, L. Yung, Ö. Çetin, J. Frankel, S. King, M. Magimai-Doss, X. Chi, and L. Lavoie. Manual transcription of conversational speech at the articulatory feature level. In Proc. ICASSP, Honolulu, April 2007. [ bib | .pdf ]
We present an approach for the manual labeling of speech at the articulatory feature level, and a new set of labeled conversational speech collected using this approach. A detailed transcription, including overlapping or reduced gestures, is useful for studying the great pronunciation variability in conversational speech. It also facilitates the testing of feature classiers, such as those used in articulatory approaches to automatic speech recognition. We describe an effort to transcribe a small set of utterances drawn from the Switchboard database using eight articulatory tiers. Two transcribers have labeled these utterances in a multi-pass strategy, allowing for correction of errors. We describe the data collection methods and analyze the data to determine how quickly and reliably this type of transcription can be done. Finally, we demonstrate one use of the new data set by testing a set of multilayer perceptron feature classiers against both the manual labels and forced alignments.

[23] S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond, and M. Wester. Speech production knowledge in automatic speech recognition. Journal of the Acoustical Society of America, 121(2):723-742, February 2007. [ bib | .pdf ]
Although much is known about how speech is produced, and research into speech production has resulted in measured articulatory data, feature systems of different kinds and numerous models, speech production knowledge is almost totally ignored in current mainstream approaches to automatic speech recognition. Representations of speech production allow simple explanations for many phenomena observed in speech which cannot be easily analyzed from either acoustic signal or phonetic transcription alone. In this article, we provide a survey of a growing body of work in which such representations are used to improve automatic speech recognition.

[24] J. Frankel and S. King. Speech recognition using linear dynamic models. IEEE Transactions on Speech and Audio Processing, 15(1):246-256, January 2007. [ bib | .ps | .pdf ]
The majority of automatic speech recognition (ASR) systems rely on hidden Markov models, in which Gaussian mixtures model the output distributions associated with sub-phone states. This approach, whilst successful, models consecutive feature vectors (augmented to include derivative information) as statistically independent. Furthermore, spatial correlations present in speech parameters are frequently ignored through the use of diagonal covariance matrices. This paper continues the work of Digalakis and others who proposed instead a first-order linear state-space model which has the capacity to model underlying dynamics, and furthermore give a model of spatial correlations. This paper examines the assumptions made in applying such a model and shows that the addition of a hidden dynamic state leads to increases in accuracy over otherwise equivalent static models. We also propose a time-asynchronous decoding strategy suited to recognition with segment models. We describe implementation of decoding for linear dynamic models and present TIMIT phone recognition results.

[25] J. Frankel and S. King. Observation process adaptation for linear dynamic models. Speech Communication, 48(9):1192-1199, September 2006. [ bib | .ps | .pdf ]
This work introduces two methods for adapting the observation process parameters of linear dynamic models (LDM) or other linear-Gaussian models. The first method uses the expectation-maximization (EM) algorithm to estimate transforms for location and covariance parameters, and the second uses a generalized EM (GEM) approach which reduces computation in making updates from O(p6) to O(p3), where p is the feature dimension. We present the results of speaker adaptation on TIMIT phone classification and recognition experiments with relative error reductions of up to 6%. Importantly, we find minimal differences in the results from EM and GEM. We therefore propose that the GEM approach be applied to adaptation of hidden Markov models which use non-diagonal covariances. We provide the necessary update equations.

[26] A. Janin, A. Stolcke, X. Anguera, K. Boakye, Ö. Çetin, J. Frankel, and J. Zheng. The ICSI-SRI spring 2006 meeting recognition system. In Proc. MLMI, Washington DC., May 2006. [ bib | .ps | .pdf ]
We describe the development of the ICSI-SRI speech recognition system for the National Institute of Standards and Technology (NIST) Spring 2006 Meeting Rich Transcription (RT-06S) evaluation, highlighting improvements made since last year, including improvements to the delay-and-sum algorithm, the nearfield segmenter, language models, posterior-based features, HMM adaptation methods, and adapting to a small amount of new lecture data. Results are reported on RT-05S and RT-06S meeting data. Compared to the RT-05S conference system, we achieved an overall improvement of 4% relative in the MDM and SDM conditions, and 11% relative in the IHM condition. On lecture data, we achieved an overall improvement of 8% relative in the SDM condition, 12% on MDM, 14% on ADM, and 15% on IHM.

[27] J. Frankel and S. King. A hybrid ANN/DBN approach to articulatory feature recognition. In Proc. Eurospeech, Lisbon, September 2005. [ bib | .ps | .pdf ]
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (AF) recognition. Previous studies have taken a cascaded approach where separate ANNs are trained for each feature group, making the assumption that features are statistically independent. We address this by using ANNs to provide virtual evidence to a dynamic Bayesian network (DBN). This gives a hybrid ANN/DBN model and allows modelling of inter-feature dependencies. We demonstrate significant increases in AF recognition accuracy from modelling dependencies between features, and present the results of embedded training experiments in which a set of asynchronous feature changes are learned. Furthermore, we report on the application of a Viterbi training scheme in which we alternate between realigning the AF training labels and retraining the ANNs.

[28] M. Wester, J. Frankel, and S. King. Asynchronous articulatory feature recognition using dynamic Bayesian networks. In Proc. IEICI Beyond HMM Workshop, Kyoto, December 2004. [ bib | .ps | .pdf ]
This paper builds on previous work where dynamic Bayesian networks (DBN) were proposed as a model for articulatory feature recognition. Using DBNs makes it possible to model the dependencies between features, an addition to previous approaches which was found to improve feature recognition performance. The DBN results were promising, giving close to the accuracy of artificial neural nets (ANNs). However, the system was trained on canonical labels, leading to an overly strong set of constraints on feature co-occurrence. In this study, we describe an embedded training scheme which learns a set of data-driven asynchronous feature changes where supported in the data. Using a subset of the OGI Numbers corpus, we describe articulatory feature recognition experiments using both canonically-trained and asynchronous DBNs. Performance using DBNs is found to exceed that of ANNs trained on an identical task, giving a higher recognition accuracy. Furthermore, inter-feature dependencies result in a more structured model, giving rise to fewer feature combinations in the recognition output. In addition to an empirical evaluation of this modelling approach, we give a qualitative analysis, comparing asynchrony found through our data-driven methods to the asynchrony which may be expected on the basis of linguistic knowledge.

[29] J. Frankel, M. Wester, and S. King. Articulatory feature recognition using dynamic Bayesian networks. In Proc. ICSLP, September 2004. [ bib | .ps | .pdf ]
This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recognition. We show that by modeling the dependencies between a set of 6 multi-leveled articulatory features, recognition accuracy is increased over an equivalent system in which features are considered independent. Results are compared to those found using artificial neural networks on an identical task.

[30] J. Frankel. Linear dynamic models for automatic speech recognition. PhD thesis, The Centre for Speech Technology Research, Edinburgh University, April 2003. [ bib | .ps | .pdf ]
The majority of automatic speech recognition (ASR) systems rely on hidden Markov models (HMM), in which the output distribution associated with each state is modelled by a mixture of diagonal covariance Gaussians. Dynamic information is typically included by appending time-derivatives to feature vectors. This approach, whilst successful, makes the false assumption of framewise independence of the augmented feature vectors and ignores the spatial correlations in the parametrised speech signal. This dissertation seeks to address these shortcomings by exploring acoustic modelling for ASR with an application of a form of state-space model, the linear dynamic model (LDM). Rather than modelling individual frames of data, LDMs characterize entire segments of speech. An auto-regressive state evolution through a continuous space gives a Markovian model of the underlying dynamics, and spatial correlations between feature dimensions are absorbed into the structure of the observation process. LDMs have been applied to speech recognition before, however a smoothed Gauss-Markov form was used which ignored the potential for subspace modelling. The continuous dynamical state means that information is passed along the length of each segment. Furthermore, if the state is allowed to be continuous across segment boundaries, long range dependencies are built into the system and the assumption of independence of successive segments is loosened. The state provides an explicit model of temporal correlation which sets this approach apart from frame-based and some segment-based models where the ordering of the data is unimportant. The benefits of such a model are examined both within and between segments. LDMs are well suited to modelling smoothly varying, continuous, yet noisy trajectories such as found in measured articulatory data. Using speaker-dependent data from the MOCHA corpus, the performance of systems which model acoustic, articulatory, and combined acoustic-articulatory features are compared. As well as measured articulatory parameters, experiments use the output of neural networks trained to perform an articulatory inversion mapping. The speaker-independent TIMIT corpus provides the basis for larger scale acoustic-only experiments. Classification tasks provide an ideal means to compare modelling choices without the confounding influence of recognition search errors, and are used to explore issues such as choice of state dimension, front-end acoustic parametrization and parameter initialization. Recognition for segment models is typically more computationally expensive than for frame-based models. Unlike frame-level models, it is not always possible to share likelihood calculations for observation sequences which occur within hypothesized segments that have different start and end times. Furthermore, the Viterbi criterion is not necessarily applicable at the frame level. This work introduces a novel approach to decoding for segment models in the form of a stack decoder with A* search. Such a scheme allows flexibility in the choice of acoustic and language models since the Viterbi criterion is not integral to the search, and hypothesis generation is independent of the particular language model. Furthermore, the time-asynchronous ordering of the search means that only likely paths are extended, and so a minimum number of models are evaluated. The decoder is used to give full recognition results for feature-sets derived from the MOCHA and TIMIT corpora. Conventional train/test divisions and choice of language model are used so that results can be directly compared to those in other studies. The decoder is also used to implement Viterbi training, in which model parameters are alternately updated and then used to re-align the training data.

[31] J. Frankel and S. King. ASR - articulatory speech recognition. In Proc. Eurospeech, pages 599-602, Aalborg, Denmark, September 2001. [ bib | .ps | .pdf ]
In this paper we report recent work on a speech recognition system using a combination of acoustic and articulatory features as input. Linear dynamic models are used to capture the trajectories which characterize each segment type. We describe classification and recognition tasks for systems based on acoustic data in conjunction with both real and automatically recovered articulatory parameters.

[32] J. Frankel and S. King. Speech recognition in the articulatory domain: investigating an alternative to acoustic HMMs. In Proc. Workshop on Innovations in Speech Processing, April 2001. [ bib | .ps | .pdf ]
We describe a speech recognition system which uses a combination of acoustic and articulatory features as input. Linear dynamic models capture the trajectories which characterize each segment type. We describe classification and recognition tasks for systems based on acoustic data in conjunction with both real and automatically recovered articulatory parameters.

[33] J. Frankel, K. Richmond, S. King, and P. Taylor. An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces. In Proc. ICSLP, 2000. [ bib | .ps | .pdf ]
In this paper we describe a speech recognition system using linear dynamic models and articulatory features. Experiments are reported in which measured articulation from the MOCHA corpus has been used, along with those where the articulatory parameters are estimated from the speech signal using a recurrent neural network.

[34] S. King, P. Taylor, J. Frankel, and K. Richmond. Speech recognition via phonetically-featured syllables. In PHONUS, volume 5, pages 15-34, Institute of Phonetics, University of the Saarland, 2000. [ bib | .ps | .pdf ]
We describe recent work on two new automatic speech recognition systems. The first part of this paper describes the components of a system based on phonological features (which we call EspressoA) in which the values of these features are estimated from the speech signal before being used as the basis for recognition. In the second part of the paper, another system (which we call EspressoB) is described in which articulatory parameters are used instead of phonological features and a linear dynamical system model is used to perform recognition from automatically estimated values of these articulatory parameters.