With ageing, human voices undergo several changes which are typically characterised by increased hoarseness, breathiness, changes in articulatory patterns and slower speaking rate. The focus of this thesis is to understand the impact of ageing on Automatic Speech Recognition (ASR) performance and improve the ASR accuracies for older voices. Baseline results on three corpora indicate that the word error rates (WER) for older adults are significantly higher than those of younger adults and the decrease in accuracies is higher for males speakers as compared to females. Acoustic parameters such as jitter and shimmer that measure glottal source disfluencies were found to be significantly higher for older adults. However, the hypothesis that these changes explain the differences in WER for the two age groups is proven incorrect. Experiments with artificial introduction of glottal source disfluencies in speech from younger adults do not display a significant impact on WERs. Changes in fundamental frequency observed quite often in older voices has a marginal impact on ASR accuracies. Analysis of phoneme errors between younger and older speakers shows a pattern of certain phonemes especially lower vowels getting more affected with ageing. These changes however are seen to vary across speakers. Another factor that is strongly associated with ageing voices is a decrease in the rate of speech. Experiments to analyse the impact of slower speaking rate on ASR accuracies indicate that the insertion errors increase while decoding slower speech with models trained on relatively faster speech. We then propose a way to characterise speakers in acoustic space based on speaker adaptation transforms and observe that speakers (especially males) can be segregated with reasonable accuracies based on age. Inspired by this, we look at supervised hierarchical acoustic models based on gender and age. Significant improvements in word accuracies are achieved over the baseline results with such models. The idea is then extended to construct unsupervised hierarchical models which also outperform the baseline models by a good margin. Finally, we hypothesize that the ASR accuracies can be improved by augmenting the adaptation data with speech from acoustically closest speakers. A strategy to select the augmentation speakers is proposed. Experimental results on two corpora indicate that the hypothesis holds true only when the amount of available adaptation is limited to a few seconds. The efficacy of such a speaker selection strategy is analysed for both younger and older adults.

O presente trabalho descreve duas técnicas de adaptação ao locutor para sistemas de reconhecimento de voz utilizando um volume de dados de adaptação reduzido. Regressão Linear de Máxima Verossimilhança (MLLR) e Autovozes são as técnicas trabalhadas. Ambas atualizam as médias das Gaussianas dos modelos ocultos de Markov (HMM). A técnica MLLR estima um grupo de transformações lineares para os parâmetros das medias das Gaussianas do sistema. A técnica de Autovozes baseia-se no conhecimento prévio das variações entre locutores. Para obtermos o conhecimento prévio, que está contido nas autovozes, utiliza-se a análise em componentes principais (PCA). Fizemos os testes de adaptação das médias em um sistema de reconhecimento de voz de palavras isoladas e de vocabulário restrito. Contando com um volume grande de dados de adaptação (mais de 70% das palavras do vocabulário) a técnica de autovozes não apresentou resultados expressivos com relação aos que a técnica MLLR apresentou. Agora, quando o volume de dados reduzido (menos de 15% das palavras do vocabulário) a técnica de Autovozes apresentou-se superior à MLLR. / This present work describe two speaker adaptation technique, using a small amount of adaptation data, for a speech recognition system. These techniques are Maximum Likelihood Linear Regression (MLLR) and Eigenvoices. Both re-estimates the mean of a continuous density Hidden Markov Model system. MLLR technique estimates a set of linear transformations for mean parameters of a Gaussian system. The eigenvoice technique is based on a previous knowledge about speaker variation. For obtaining this previous knowledge, that are retained in eigenvoices, it necessary to apply principal component analysis (PCA). We make adaptation tests over an isolated word recognition system, restrict vocabulary. If a large amount of adaptation data is available (up to 70% of all vocabulary) Eigenvoices technique does not appear to be a good implementation if compared with the MLLR technique. Now, when just a small amount of adaptation data is available (less than 15 % of all vocabulary), Eigenvoices technique get better results than MLLR technique.

O presente trabalho descreve duas técnicas de adaptação ao locutor para sistemas de reconhecimento de voz utilizando um volume de dados de adaptação reduzido. Regressão Linear de Máxima Verossimilhança (MLLR) e Autovozes são as técnicas trabalhadas. Ambas atualizam as médias das Gaussianas dos modelos ocultos de Markov (HMM). A técnica MLLR estima um grupo de transformações lineares para os parâmetros das medias das Gaussianas do sistema. A técnica de Autovozes baseia-se no conhecimento prévio das variações entre locutores. Para obtermos o conhecimento prévio, que está contido nas autovozes, utiliza-se a análise em componentes principais (PCA). Fizemos os testes de adaptação das médias em um sistema de reconhecimento de voz de palavras isoladas e de vocabulário restrito. Contando com um volume grande de dados de adaptação (mais de 70% das palavras do vocabulário) a técnica de autovozes não apresentou resultados expressivos com relação aos que a técnica MLLR apresentou. Agora, quando o volume de dados reduzido (menos de 15% das palavras do vocabulário) a técnica de Autovozes apresentou-se superior à MLLR. / This present work describe two speaker adaptation technique, using a small amount of adaptation data, for a speech recognition system. These techniques are Maximum Likelihood Linear Regression (MLLR) and Eigenvoices. Both re-estimates the mean of a continuous density Hidden Markov Model system. MLLR technique estimates a set of linear transformations for mean parameters of a Gaussian system. The eigenvoice technique is based on a previous knowledge about speaker variation. For obtaining this previous knowledge, that are retained in eigenvoices, it necessary to apply principal component analysis (PCA). We make adaptation tests over an isolated word recognition system, restrict vocabulary. If a large amount of adaptation data is available (up to 70% of all vocabulary) Eigenvoices technique does not appear to be a good implementation if compared with the MLLR technique. Now, when just a small amount of adaptation data is available (less than 15 % of all vocabulary), Eigenvoices technique get better results than MLLR technique.

Confidence measures for the results of speech/speaker recognition make the systems more useful in the real time applications. Confidence measures provide a test statistic for accepting or rejecting the recognition hypothesis of the speech/speaker recognition system. Speech/speaker recognition systems are usually based on statistical modeling techniques. In this thesis we defined confidence measures for statistical modeling techniques used in speech/speaker recognition systems. For speech recognition we tested available confidence measures and the newly defined acoustic prior information based confidence measure in two different conditions which cause errors: the out-of-vocabulary words and presence of additive noise. We showed that the newly defined confidence measure performs better in both tests. Review of speech recognition and speaker recognition techniques and some related statistical methods is given through the thesis. We defined also a new interpretation technique for confidence measures which is based on Fisher transformation of likelihood ratios obtained in speaker verification. Transformation provided us with a linearly interpretable confidence level which can be used directly in real time applications like for dialog management. We have also tested the confidence measures for speaker verification systems and evaluated the efficiency of the confidence measures for adaptation of speaker models. We showed that use of confidence measures to select adaptation data improves the accuracy of the speaker model adaptation process. Another contribution of this thesis is the preparation of a phonetically rich continuous speech database for Turkish Language. The database is used for developing an HMM/MLP hybrid speech recognition for Turkish Language. Experiments on the test sets of the database showed that the speech recognition system has a good accuracy for long speech sequences while performance is lower for short words, as it is the case for current speech recognition systems for other languages. A new language modeling technique for the Turkish language is introduced in this thesis, which can be used for other agglutinative languages. Performance evaluations on newly defined language modeling techniques showed that it outperforms the classical n-gram language modeling technique.

This thesis considers the entire automated speech recognition process and presents a standardised approach to LVCSR experimentation with HMMs. It also discusses various approaches to speaker adaptation such as MLLR and multiscale, and presents experimental results for cross­-task speaker adaptation. An analysis of training parameters and data sufficiency for reasonable system performance estimates are also included. It is found that Maximum Likelihood Linear Regression (MLLR) supervised adaptation can result in 6% reduction (absolute) in word error rate given only one minute of adaptation data, as compared with an unadapted model set trained on a different task. The unadapted system performed at 24% WER and the adapted system at 18% WER. This is achieved with only 4 to 7 adaptation classes per speaker, as generated from a regression tree.

This thesis considers the entire automated speech recognition process and presents a standardised approach to LVCSR experimentation with HMMs. It also discusses various approaches to speaker adaptation such as MLLR and multiscale, and presents experimental results for cross­-task speaker adaptation. An analysis of training parameters and data sufficiency for reasonable system performance estimates are also included. It is found that Maximum Likelihood Linear Regression (MLLR) supervised adaptation can result in 6% reduction (absolute) in word error rate given only one minute of adaptation data, as compared with an unadapted model set trained on a different task. The unadapted system performed at 24% WER and the adapted system at 18% WER. This is achieved with only 4 to 7 adaptation classes per speaker, as generated from a regression tree.

No description available.

This master's thesis deals with design and developement of simple dictation system. It explains methods used for speech recognition and describes existing systems. Design of the system is focused primarily to create graphic user interface with large emphasis on user friendliness.

The field of speech recognition during the last decade has left the research stage and found its way into the public market, and today, speech recognition software is ubiquitous around us. An automatic speech recognizer understands human speech and represents it as text. Most of the current speech recognition software employs variants of deep neural networks. Before the deep learning era, the hybrid of hidden Markov model and Gaussian mixture model (HMM-GMM) was a popular statistical model to solve speech recognition. In this thesis, automatic speech recognition using HMM-GMM was trained on Somali data which consisted of voice recording and its transcription. HMM-GMM is a hybrid system in which the framework is composed of an acoustic model and a language model. The acoustic model represents the time-variant aspect of the speech signal, and the language model determines how probable is the observed sequence of words. This thesis begins with background about speech recognition. Literature survey covers some of the work that has been done in this field. This thesis evaluates how different language models and discounting methods affect the performance of speech recognition systems. Also, log scores were calculated for the top 5 predicted sentences and confidence measures of pre-dicted sentences. The model was trained on 4.5 hrs of voiced data and its corresponding transcription. It was evaluated on 3 mins of testing data. The performance of the trained model on the test set was good, given that the data was devoid of any background noise and lack of variability. The performance of the model is measured using word error rate(WER) and sentence error rate (SER). The performance of the implemented model is also compared with the results of other research work. This thesis also discusses why log and confidence score of the sentence might not be a good way to measure the performance of the resulting model. It also discusses the shortcoming of the HMM-GMM model, how the existing model can be improved, and different alternatives to solve the problem.

Les sons de parole peuvent être complétés par l'affichage des articulateurs sur un écran d'ordinateur pour produire de la parole augmentée, un signal potentiellement utile dans tous les cas où le son lui-même peut être difficile à comprendre, pour des raisons physiques ou perceptuelles. Dans cette thèse, nous présentons un système appelé retour articulatoire visuel, dans lequel les articulateurs visibles et non visibles d'une tête parlante sont contrôlés à partir de la voix du locuteur. La motivation de cette thèse était de développer un tel système qui pourrait être appliqué à l'aide à l'apprentissage de la prononciation pour les langues étrangères, ou dans le domaine de l'orthophonie. Nous avons basé notre approche de ce problème d'inversion sur des modèles statistiques construits à partir de données acoustiques et articulatoires enregistrées sur un locuteur français à l'aide d'un articulographe électromagnétique (EMA). Notre approche avec les modèles de Markov cachés (HMMs) combine des techniques de reconnaissance automatique de la parole et de synthèse articulatoire pour estimer les trajectoires articulatoires à partir du signal acoustique. D'un autre côté, les modèles de mélanges gaussiens (GMMs) estiment directement les trajectoires articulatoires à partir du signal acoustique sans faire intervenir d'information phonétique. Nous avons basé notre évaluation des améliorations apportées à ces modèles sur différents critères : l'erreur quadratique moyenne (RMSE) entre les coordonnées EMA originales et reconstruites, le coefficient de corrélation de Pearson, l'affichage des espaces et des trajectoires articulatoires, aussi bien que les taux de reconnaissance acoustique et articulatoire. Les expériences montrent que l'utilisation d'états liés et de multi-gaussiennes pour les états des HMMs acoustiques améliore l'étage de reconnaissance acoustique des phones, et que la minimisation de l'erreur générée (MGE) dans la phase d'apprentissage des HMMs articulatoires donne des résultats plus précis par rapport à l'utilisation du critère plus conventionnel de maximisation de vraisemblance (MLE). En outre, l'utilisation du critère MLE au niveau de mapping direct de l'acoustique vers l'articulatoire par GMMs est plus efficace que le critère de minimisation de l'erreur quadratique moyenne (MMSE). Nous constatons également trouvé que le système d'inversion par HMMs est plus précis celui basé sur les GMMs. Par ailleurs, des expériences utilisant les mêmes méthodes statistiques et les mêmes données ont montré que le problème de reconstruction des mouvements de la langue à partir des mouvements du visage et des lèvres ne peut pas être résolu dans le cas général, et est impossible pour certaines classes phonétiques. Afin de généraliser notre système basé sur un locuteur unique à un système d'inversion de parole multi-locuteur, nous avons implémenté une méthode d'adaptation du locuteur basée sur la maximisation de la vraisemblance par régression linéaire (MLLR). Dans cette méthode MLLR, la transformation basée sur la régression linéaire qui adapte les HMMs acoustiques originaux à ceux du nouveau locuteur est calculée de manière à maximiser la vraisemblance des données d'adaptation. Finalement, cet étage d'adaptation du locuteur a été évalué en utilisant un système de reconnaissance automatique des classes phonétique de l'articulation, dans la mesure où les données articulatoires originales du nouveau locuteur n'existent pas. Finalement, en utilisant cette procédure d'adaptation, nous avons développé un démonstrateur complet de retour articulatoire visuel, qui peut être utilisé par un locuteur quelconque. Ce système devra être évalué de manière perceptive dans des conditions réalistes. / Speech sounds may be complemented by displaying speech articulators shapes on a computer screen, hence producing augmented speech, a signal that is potentially useful in all instances where the sound itself might be difficult to understand, for physical or perceptual reasons. In this thesis, we introduce a system called visual articulatory feedback, in which the visible and hidden articulators of a talking head are controlled from the speaker's speech sound. The motivation of this research was to develop such a system that could be applied to Computer Aided Pronunciation Training (CAPT) for learning of foreign languages, or in the domain of speech therapy. We have based our approach to this mapping problem on statistical models build from acoustic and articulatory data. In this thesis we have developed and evaluated two statistical learning methods trained on parallel synchronous acoustic and articulatory data recorded on a French speaker by means of an electromagnetic articulograph. Our Hidden Markov models (HMMs) approach combines HMM-based acoustic recognition and HMM-based articulatory synthesis techniques to estimate the articulatory trajectories from the acoustic signal. Gaussian mixture models (GMMs) estimate articulatory features directly from the acoustic ones. We have based our evaluation of the improvement results brought to these models on several criteria: the Root Mean Square Error between the original and recovered EMA coordinates, the Pearson Product-Moment Correlation Coefficient, displays of the articulatory spaces and articulatory trajectories, as well as some acoustic or articulatory recognition rates. Experiments indicate that the use of states tying and multi-Gaussian per state in the acoustic HMM improves the recognition stage, and that the minimum generation error (MGE) articulatory HMMs parameter updating results in a more accurate inversion than the conventional maximum likelihood estimation (MLE) training. In addition, the GMM mapping using MLE criteria is more efficient than using minimum mean square error (MMSE) criteria. In conclusion, we have found that the HMM inversion system has a greater accuracy compared with the GMM one. Beside, experiments using the same statistical methods and data have shown that the face-to-tongue inversion problem, i.e. predicting tongue shapes from face and lip shapes cannot be solved in a general way, and that it is impossible for some phonetic classes. In order to extend our system based on a single speaker to a multi-speaker speech inversion system, we have implemented a speaker adaptation method based on the maximum likelihood linear regression (MLLR). In MLLR, a linear regression-based transform that adapts the original acoustic HMMs to those of the new speaker was calculated to maximise the likelihood of adaptation data. Finally, this speaker adaptation stage has been evaluated using an articulatory phonetic recognition system, as there are not original articulatory data available for the new speakers. Finally, using this adaptation procedure, we have developed a complete articulatory feedback demonstrator, which can work for any speaker. This system should be assessed by perceptual tests in realistic conditions.