Improving reverberant VTS for hands-free robust speech recognition

Model-based approaches to handling additive background noise and channel distortion, such as Vector Taylor Series (VTS), have been intensively studied and extended in a number of ways. In previous work, VTS has been extended to handle both reverberant and background noise, yielding the Reverberant VTS (RVTS) scheme. In this work, rather than assuming the observation vector is generated by the reverberation of a sequence of background noise corrupted speech vectors, as in RVTS, the observation vector is modelled as a superposition of the background noise and the reverberation of clean speech. This yields a new compensation scheme RVTS Joint (RVTSJ), which allows an easy formulation for joint estimation of both additive and reverberation noise parameters. These two compensation schemes were evaluated and compared on a simulated reverberant noise corrupted AURORA4 task. Both yielded large gains over VTS baseline system, with RVTSJ outperforming the previous RVTS scheme. © 2011 IEEE.

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.

Compression techniques applied to multiple speech recognition systems

Speech recognition systems typically contain many Gaussian distributions, and hence a large number of parameters. This makes them both slow to decode speech, and large to store. Techniques have been proposed to decrease the number of parameters. One approach is to share parameters between multiple Gaussians, thus reducing the total number of parameters and allowing for shared likelihood calculation. Gaussian tying and subspace clustering are two related techniques which take this approach to system compression. These techniques can decrease the number of parameters with no noticeable drop in performance for single systems. However, multiple acoustic models are often used in real speech recognition systems. This paper considers the application of Gaussian tying and subspace compression to multiple systems. Results show that two speech recognition systems can be modelled using the same number of Gaussians as just one system, with little effect on individual system performance. Copyright © 2009 ISCA.

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.

Word boundary modelling and full covariance gaussians for Arabic Speech-to-Text systems

This paper describes recent improvements to the Cambridge Arabic Large Vocabulary Continuous Speech Recognition (LVCSR) Speech-to-Text (STT) system. It is shown that wordboundary context markers provide a powerful method to enhance graphemic systems by implicit phonetic information, improving the modelling capability of graphemic systems. In addition, a robust technique for full covariance Gaussian modelling in the Minimum Phone Error (MPE) training framework is introduced. This reduces the full covariance training to a diagonal covariance training problem, thereby solving related robustness problems. The full system results show that the combined use of these and other techniques within a multi-branch combination framework reduces the Word Error Rate (WER) of the complete system by up to 5.9% relative. Copyright © 2011 ISCA.

Syllable language models for Mandarin speech recognition: exploiting character language models.

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

Vowel normalisation: Time-domain processing of the internal dynamics of speech

Human listeners can identify vowels regardless of speaker size, although the sound waves for an adult and a child speaking the ’same’ vowel would differ enormously. The differences are mainly due to the differences in vocal tract length (VTL) and glottal pulse rate (GPR) which are both related to body size. Automatic speech recognition machines are notoriously bad at understanding children if they have been trained on the speech of an adult. In this paper, we propose that the auditory system adapts its analysis of speech sounds, dynamically and automatically to the GPR and VTL of the speaker on a syllable-to-syllable basis. We illustrate how this rapid adaptation might be performed with the aid of a computational version of the auditory image model, and we propose that an auditory preprocessor of this form would improve the robustness of speech recognisers.