Publications by Rob Clark

Spontaneous conversational speech has many characteristics that are currently not modelled well by HMM-based speech synthesis and in order to build synthetic voices that can give an impression of someone partaking in a conversation, we need to utilise data that exhibits more of the speech phenomena associated with conversations than the more generally used carefully read aloud sentences. In this paper we show that synthetic voices built with HMM-based speech synthesis techniques from conversational speech data, preserved segmental and prosodic characteristics of frequent conversational speech phenomena. An analysis of an evaluation investigating the perception of quality and speaking style of HMM-based voices confirms that speech with conversational characteristics are instrumental for listeners to perceive successful integration of conversational speech phenomena in synthetic speech. The achieved synthetic speech quality provides an encouraging start for the continued use of conversational speech in HMM-based speech synthesis.

The quality of current commercial speech synthesis systems is now so high that system improvements are being made at subtle sub- and supra-segmental levels. Human perceptual evaluation of such subtle improvements requires a highly sophisticated level of perceptual attention to specific acoustic characteristics or cues. However, it is not well understood what acoustic cues listeners attend to by default when asked to evaluate synthetic speech. It may, therefore, be potentially quite difficult to design an evaluation method that allows listeners to concentrate on only one dimension of the signal, while ignoring others that are perceptually more important to them. The aim of the current study was to determine which acoustic characteristics of unit-selection synthetic speech are most salient to listeners when evaluating the naturalness of such speech. This study made use of multidimensional scaling techniques to analyse listeners' pairwise comparisons of synthetic speech sentences. Results indicate that listeners place a great deal of perceptual importance on the presence of artifacts and discontinuities in the speech, somewhat less importance on aspects of segmental quality, and very little importance on stress/intonation appropriateness. These relative differences in importance will impact on listeners' ability to attend to these different acoustic characteristics of synthetic speech, and should therefore be taken into account when designing appropriate methods of synthetic speech evaluation.

Keywords: Speech synthesis; Evaluation; Speech perception; Acoustic cue weighting; Multidimensional scaling

Combilex is a high-quality lexicon that has been developed specifically for speech technology purposes and recently released by CSTR. Combilex benefits from many advanced features. This paper explores one of these: the ability to generate fully-specified transcriptions for morphologically derived words automatically. This functionality was originally implemented to encode the pronunciations of derived words in terms of their constituent morphemes, thus accelerating lexicon development and ensuring a high level of consistency. In this paper, we propose this method of modelling pronunciations can be exploited further by combining it with a morphological parser, thus yielding a method to generate full transcriptions for unknown derived words. Not only could this accelerate adding new derived words to Combilex, but it could also serve as an alternative to conventional letter-to-sound rules. This paper presents preliminary work indicating this is a promising direction.

Keywords: combilex lexicon, letter-to-sound rules, grapheme-to-phoneme conversion, morphological decomposition

Spontaneous conversational speech has many characteristics that are currently not well modelled in unit selection and HMM-based speech synthesis. But in order to build synthetic voices more suitable for interaction we need data that exhibits more conversational characteristics than the generally used read aloud sentences. In this paper we will show how carefully selected utterances from a spontaneous conversation was instrumental for building an HMM-based synthetic voices with more natural sounding conversational characteristics than a voice based on carefully read aloud sentences. We also investigated a style blending technique as a solution to the inherent problem of phonetic coverage in spontaneous speech data. But the lack of an appropriate representation of spontaneous speech phenomena probably contributed to results showing that we could not yet compete with the speech quality achieved for grammatical sentences.

Unit selection speech synthesis has reached high levels of naturalness and intelligibility for neutral read aloud speech. However, synthetic speech generated using neutral read aloud data lacks all the attitude, intention and spontaneity associated with everyday conversations. Unit selection is heavily data dependent and thus in order to simulate human conversational speech, or create synthetic voices for believable virtual characters, we need to utilise speech data with examples of how people talk rather than how people read. In this paper we included carefully selected utterances from spontaneous conversational speech in a unit selection voice. Using this voice and by automatically predicting type and placement of lexical fillers and filled pauses we can synthesise utterances with conversational characteristics. A perceptual listening test showed that it is possible to make synthetic speech sound more conversational without degrading naturalness.

The difference between native speakers' and non-native speak- ers' naturalness judgements of synthetic speech is investigated. Similar/difference judgements are analysed via a multidimensional scaling analysis and compared to Mean opinion scores. It is shown that although the two groups generally behave in a similar manner the variance of non-native speaker judgements is generally higher. While both groups of subject can clearly distinguish natural speech from the best synthetic examples, the groups' responses to different artefacts present in the synthetic speech can vary.

Generating responses that take user preferences into account requires adaptation at all levels of the generation process. This article describes a multi-level approach to presenting user-tailored information in spoken dialogues which brings together for the first time multi-attribute decision models, strategic content planning, surface realization that incorporates prosody prediction, and unit selection synthesis that takes the resulting prosodic structure into account. The system selects the most important options to mention and the attributes that are most relevant to choosing between them, based on the user model. Multiple options are selected when each offers a compelling trade-off. To convey these trade-offs, the system employs a novel presentation strategy which straightforwardly lends itself to the determination of information structure, as well as the contents of referring expressions. During surface realization, the prosodic structure is derived from the information structure using Combinatory Categorial Grammar in a way that allows phrase boundaries to be determined in a flexible, data-driven fashion. This approach to choosing pitch accents and edge tones is shown to yield prosodic structures with significantly higher acceptability than baseline prosody prediction models in an expert evaluation. These prosodic structures are then shown to enable perceptibly more natural synthesis using a unit selection voice that aims to produce the target tunes, in comparison to two baseline synthetic voices. An expert evaluation and f0 analysis confirm the superiority of the generator-driven intonation and its contribution to listeners' ratings.

Multidimensional scaling (MDS) has been suggested as a use- ful tool for the evaluation of the quality of synthesized speech. However, it has not yet been extensively tested for its applica- tion in this specific area of evaluation. In a series of experi- ments based on data from the Blizzard Challenge 2008 the relations between Weighted Euclidean Distance Scaling and Simple Euclidean Distance Scaling is investigated to understand how aggregating data affects the MDS configuration. These results are compared to those collected as mean opinion scores (MOS). The ranks correspond, and MOS can be predicted from an object's space in the MDS generated stimulus space. The big advantage of MDS over MOS is its diagnostic value; dimensions along which stimuli vary are not correlated, as is the case in modular evaluation using MOS. Finally, it will be attempted to generalize from the MDS representations of the thoroughly tested subset to the aggregated data of the larger-scale Blizzard Challenge.

This paper describes the CSTR entry for the Blizzard Challenge 2009. The work focused on modifying two parts of the Nitech 2005 HTS speech synthesis system to improve naturalness and contextual appropriateness. The first part incorporated an implementation of the Linjencrants-Fant (LF) glottal source model. The second part focused on improving synthesis of prosodic prominence including emphasis through context dependent phonemes. Emphasis was assigned to the synthesised test sentences based on a handful of theory based rules. The two parts (LF-model and prosodic prominence) were not combined and hence evaluated separately. The results on naturalness for the LF-model showed that it is not yet perceived as natural as the Benchmark HTS system for neutral speech. The results for the prosodic prominence modelling showed that it was perceived as contextually appropriate as the Benchmark HTS system, despite a low naturalness score. The Blizzard challenge evaluation has provided valuable information on the status of our work and continued work will begin with analysing why our modifications resulted in reduced naturalness compared to the Benchmark HTS system.

The work presented in this paper proposes to identify contrast in the form of contrastive word pairs and prosodically signal it with emphatic accents in a Text-to-Speech (TTS) application using a Hidden-Markov-Model (HMM) based speech synthesis system. We first describe a novel method to automatically detect contrastive word pairs using textual features only and report its performance on a corpus of spontaneous conversations in English. Subsequently we describe the set of features selected to train a HMM-based speech synthesis system and attempting to properly control prosodic prominence (including emphasis). Results from a large scale perceptual test show that in the majority of cases listeners judge emphatic contrastive word pairs as acceptable as their non-emphatic counterpart, while emphasis on non-contrastive pairs is almost never acceptable.

Combilex is a high quality pronunciation lexicon aimed at speech technology applications that has recently been released by CSTR. Combilex benefits from several advanced features. This paper evaluates one of these: the explicit alignment of phones to graphemes in a word. This alignment can help to rapidly develop robust and accurate letter-to-sound (LTS) rules, without needing to rely on automatic alignment methods. To evaluate this, we used Festival's LTS module, comparing its standard automatic alignment with Combilex's explicit alignment. Our results show using Combilex's alignment improves LTS accuracy: 86.50% words correct as opposed to 84.49%, with our most general form of lexicon. In addition, building LTS models is greatly accelerated, as the need to list allowed alignments is removed. Finally, loose comparison with other studies indicates Combilex is a superior quality lexicon in terms of consistency and size.

Keywords: combilex, letter-to-sound rules, grapheme-to-phoneme conversion

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.

Keywords: Blizzard

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.

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.

Blizzard 2007 is the third Blizzard Challenge, in which participants build voices from a common dataset. A large listening test is conducted which allows comparison of systems in terms of naturalness and intelligibility. New sections were added to the listening test for 2007 to test the perceived similarity of the speaker's identity between natural and synthetic speech. In this paper, we present the results of the listening test and the subsequent statistical analysis.

Keywords: Blizzard

We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously prominence assignment has been mainly evaluated by computing accuracy on a prominence-labelled test set. By contrast we integrated an automatic pitch-accent classifier into the unit selection target cost and showed that listeners preferred these synthesised sentences. We also describe an improved recording script for collecting emphatic accents, and show that generating emphatic accents leads to further improvements in the fiction genre over incorporating pitch accent only. Finally, we show differences in the effects of prominence between child-directed speech and news and fiction genres. Index Terms: speech synthesis, prosody, prominence, pitch accent, unit selection

This paper describes selected aspects of the Festival Multisyn entry to the Blizzard Challenge 2007. We provide an overview of the process of building the three required voices from the speech data provided. This paper focuses on new features of Multisyn which are currently under development and which have been employed in the system used for this Blizzard Challenge. These differences are the application of a more flexible phonetic lattice representation during forced alignment labelling and the use of a pitch accent target cost component. Finally, we also examine aspects of the speech data provided for this year's Blizzard Challenge and raise certain issues for discussion concerning the aim of comparing voices made with differing subsets of the data provided.

When comparing the prosodic realization of different English speakers reading the same text, a significant disagreement is usually found amongst the pitch accent patterns of the speakers. Assuming that such disagreement is due to a partial optionality of pitch accent placement, it has been recently proposed to evaluate pitch accent predictors by comparing them with multi-speaker reference data. In this paper we face the issue of pitch accent optionality at different levels. At first we propose a simple mathematical definition of intra-speaker optionality which allows us to introduce a function for evaluating pitch accent predictors which we show being more accurate and robust than those used in previous works. Subsequently we compare a pitch accent predictor trained on single speaker data with a predictor trained on multi-speaker data in order to point out the large overlapping between intra-speaker and inter-speaker optionality. Finally, we show our successful results in predicting intra-speaker optionality and we suggest how this achievement could be exploited to improve the performances of a unit selection text-to speech synthesis (TTS) system.

We present the implementation and evaluation of an open-domain unit selection speech synthesis engine designed to be flexible enough to encourage further unit selection research and allow rapid voice development by users with minimal speech synthesis knowledge and experience. We address the issues of automatically processing speech data into a usable voice using automatic segmentation techniques and how the knowledge obtained at labelling time can be exploited at synthesis time. We describe target cost and join cost implementation for such a system and describe the outcome of building voices with a number of different sized datasets. We show that, in a competitive evaluation, voices built using this technology compare favourably to other systems.

This paper describes the process of building unit selection voices for the Festival Multisyn engine using the ATR dataset provided for the Blizzard Challenge 2006. We begin by discussing recent improvements that we have made to the Multisyn voice building process, prompted by our participation in the Blizzard Challenge 2006. We then go on to discuss our interpretation of the results observed. Finally, we conclude with some comments and suggestions for the formulation of future Blizzard Challenges.

We describe a unit selection technique for text-to-speech synthesis which jointly searches the space of possible diphone sequences and the space of possible prosodic unit sequences in order to produce synthetic speech with more natural prosody. We demonstrates that this search, although currently computationally expensive, can achieve improved intonation compared to a baseline in which only the space of possible diphone sequences is searched. We discuss ways in which the search could be made sufficiently efficient for use in a real-time system.

Current unit selection speech synthesis voices cannot produce emphasis or interrogative contours because of a lack of the necessary prosodic variation in the recorded speech database. A method of recording script design is proposed which addresses this shortcoming. Appropriate components were added to the target cost function of the Festival Multisyn engine, and a perceptual evaluation showed a clear preference over the baseline system.

This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.

The goal of this project was to build a unit selection voice that could portray emotions with varying intensities. A suitable definition of an emotion was developed along with a descriptive framework that supported the work carried out. A single speaker was recorded portraying happy and angry speaking styles. Additionally a neutral database was also recorded. A target cost function was implemented that chose units according to emotion mark-up in the database. The Dictionary of Affect supported the emotional target cost function by providing an emotion rating for words in the target utterance. If a word was particularly 'emotional', units from that emotion were favoured. In addition intensity could be varied which resulted in a bias to select a greater number emotional units. A perceptual evaluation was carried out and subjects were able to recognise reliably emotions with varying amounts of emotional units present in the target utterance.

This paper describes version 2 of the Festival speech synthesis system. Festival 2 provides a development environment for concatenative speech synthesis, and now includes a general purpose unit selection speech synthesis engine. We discuss various aspects of unit selection speech synthesis, focusing on the research issues that relate to voice design and the automation of the voice development process.