Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to estimate the transcription of the adaptation data. This paper first presents an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for such supplementary acoustic models. This is achieved by defining a mapping between HMM-based synthesis models and ASR-style models, via a two-pass decision tree construction process. Second, it is shown that this mapping also enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data. Third, this paper demonstrates how this technique lends itself to the task of unsupervised cross-lingual adaptation of HMM-based speech synthesis models, and explains the advantages of such an approach. Finally, listener evaluations reveal that the proposed unsupervised adaptation methods deliver performance approaching that of supervised adaptation.

Statistical parametric speech synthesis based on speaker and language factorization

An increasingly common scenario in building speech synthesis and recognition systems is training on inhomogeneous data. This paper proposes a new framework for estimating hidden Markov models on data containing both multiple speakers and multiple languages. The proposed framework, speaker and language factorization, attempts to factorize speaker-/language-specific characteristics in the data and then model them using separate transforms. Language-specific factors in the data are represented by transforms based on cluster mean interpolation with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by transforms based on constrained maximum-likelihood linear regression. Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language. © 2012 IEEE.

Robust F0 estimation based on a multi-microphone periodicity function for distant-talking speech

This work addresses the problem of deriving F0 from distanttalking speech signals acquired by a microphone network. The method here proposed exploits the redundancy across the channels by jointly processing the different signals. To this purpose, a multi-microphone periodicity function is derived from the magnitude spectrum of all the channels. This function allows to estimate F0 reliably, even under reverberant conditions, without the need of any post-processing or smoothing technique. Experiments, conducted on real data, showed that the proposed frequency-domain algorithm is more suitable than other time-domain based ones.

Formant estimation of speech signals using subspace-based spectral analysis

The objective of this paper is to propose a signal processing scheme that employs subspace-based spectral analysis for the purpose of formant estimation of speech signals. Specifically, the scheme is based on decimative spectral estimation that uses Eigenanalysis and SVD (Singular Value Decomposition). The underlying model assumes a decomposition of the processed signal into complex damped sinusoids. In the case of formant tracking, the algorithm is applied on a small amount of the autocorrelation coefficients of a speech frame. The proposed scheme is evaluated on both artificial and real speech utterances from the TIMIT database. For the first case, comparative results to standard methods are provided which indicate that the proposed methodology successfully estimates formant trajectories.

Digits speech recognition based on geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems.We observe that this may be true for a recognition tasks based on geometrical learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions via the Hilbert transform. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy, Experiments show method based on ICA and geometrical learning outperforms HMM in different number of train samples.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Elicitation techniques for the evaluation of speech under stress: Towards a framework for use in a controlled environment

Existing work in Computer Science and Electronic Engineering demonstrates that Digital Signal Processing techniques can effectively identify the presence of stress in the speech signal. These techniques use datasets containing real or actual stress samples i.e. real-life stress such as 911 calls and so on. Studies that use simulated or laboratory-induced stress have been less successful and inconsistent. Pervasive, ubiquitous computing is increasingly moving towards voice-activated and voice-controlled systems and devices. Speech recognition and speaker identification algorithms will have to improve and take emotional speech into account. Modelling the influence of stress on speech and voice is of interest to researchers from many different disciplines including security, telecommunications, psychology, speech science, forensics and Human Computer Interaction (HCI). The aim of this work is to assess the impact of moderate stress on the speech signal. In order to do this, a dataset of laboratory-induced stress is required. While attempting to build this dataset it became apparent that reliably inducing measurable stress in a controlled environment, when speech is a requirement, is a challenging task. This work focuses on the use of a variety of stressors to elicit a stress response during tasks that involve speech content. Biosignal analysis (commercial Brain Computer Interfaces, eye tracking and skin resistance) is used to verify and quantify the stress response, if any. This thesis explains the basis of the author’s hypotheses on the elicitation of affectively-toned speech and presents the results of several studies carried out throughout the PhD research period. These results show that the elicitation of stress, particularly the induction of affectively-toned speech, is not a simple matter and that many modulating factors influence the stress response process. A model is proposed to reflect the author’s hypothesis on the emotional response pathways relating to the elicitation of stress with a required speech content. Finally the author provides guidelines and recommendations for future research on speech under stress. Further research paths are identified and a roadmap for future research in this area is defined.

Emotional speech: towards a new generation of databases

Research on speech and emotion is moving from a period of exploratory research into one where there is a prospect of substantial applications, notably in human-computer interaction. Progress in the area relies heavily on the development of appropriate databases. This paper addresses the issues that need to be considered in developing databases of emotional speech, and shows how the challenge of developing apropriate databases is being addressed in three major recent projects - the Belfast project, the Reading-Leeds project and the CREST-ESP project. From these and other studies the paper draws together the tools and methods that have been developed, addresses the problems that arise and indicates the future directions for the development of emotional speech databases.