Maximum likelihood and minimum classification error factor analysis for automatic speech recognition

Saul, Lawrence K.; Rahim, Mazin G.

doi:10.1109/89.824696

Cited by 52 publications

(30 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the definition of the factor analysis model (1) and of the distributions of the factor and the error vectors, we derive that conditional on the factors y j , the observations x j are independently distributed as t(µ + Λy j , Ψ, ν): 6 or, alternatively,…”

Section: A Mixtures Of Student's-t Factor Analyzersmentioning

confidence: 99%

“…The MFA model has been applied to a large variety of signal modeling and classification problems. Among its most typical applications, we mention speech recognition [6], textindependent speaker recognition [7], [8], face detection [9]. Nevertheless, MFA model suffers from a significant shortcoming, common to every GMM-based or GMM-related model: the model parameter estimation procedure can be adversely affected by outliers in the training data [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Signal Modeling and Classification Using a Robust Latent Space Model Based on $t$ Distributions

Chatzis

Kosmopoulos²,

Varvarigou

2008

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Factor analysis is a statistical covariance modeling technique based on the assumption of normally distributed data. A mixture of factor analyzers can be hence viewed as a special case of Gaussian (normal) mixture models providing a mathematically sound framework for attribute space dimensionality reduction. A significant shortcoming of mixtures of factor analyzers is the vulnerability of normal distributions to outliers. Recently, the replacement of normal distributions with the heavier-tailed Student's-t distributions has been proposed as a way to mitigate these shortcomings and the treatment of the resulting model under an expectation-maximization (EM) algorithm framework has been conducted. In this paper we develop a Bayesian approach to factor analysis modelling based on Student'st distributions. We derive a tractable variational inference algorithm for this model by expressing the Student's-t distributed factor analyzers as a marginalization over additional latent variables. Our innovative approach provides an efficient and more robust alternative to EM-based methods, resolving their singularity and overfitting proneness problems, while allowing for the automatic determination of the optimal model size. We demonstrate the superiority of the proposed model over well-known covariance modeling techniques in a wide range of signal processing applications.

show abstract

Section: A Mixtures Of Student's-t Factor Analyzersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Signal Modeling and Classification Using a Robust Latent Space Model Based on $t$ Distributions

Chatzis

Kosmopoulos²,

Varvarigou

2008

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

show abstract

“…The above expression is based on factor analysis which allows each of the Gaussian components to be estimated separately using EM [151]. Factor-analysed HMMs [146] generalise this to support both tying over multiple components of the loading matrices and using GMMs to model the latent variable-space of z in Figure 3.3.…”

Section: Structured Covariance Matricesmentioning

confidence: 99%

The Application of Hidden Markov Models in Speech Recognition

Gales

Young

2007

FNT in Signal Processing

438

155

View full text Add to dashboard Cite

Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs.Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication.The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.

show abstract

“…It can be used as a structured covariance matrix scheme, as an alternative to using full covariance matrices [14], [15], [17]. The generative model for the shared FA [14] extension of FA can be written as…”

Section: B Relationship To Factor Analysismentioning

confidence: 99%

Discriminative adaptive training with VTS and JUD

Flego

Gales

2009

2009 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

View full text Add to dashboard Cite

Abstract-Adaptive training is a powerful approach for building speech recognition systems on non-homogeneous training data. Recently approaches based on predictive model-based compensation schemes, such as Joint Uncertainty Decoding (JUD) and Vector Taylor Series (VTS), have been proposed. This paper reviews these model-based compensation schemes and relates them to factor-analysis style systems. Forms of Maximum Likelihood (ML) adaptive training with these approaches are described, based on both second-order optimisation schemes and Expectation Maximisation (EM). However, discriminative training is used in many state-of-the-art speech recognition. Hence, this paper proposes discriminative adaptive training with predictive model-compensation approaches for noise robust speech recognition. This training approach is applied to both JUD and VTS compensation with minimum phone error training. A large scale multi-environment training configuration is used and the systems evaluated on a range of in-car collected data tasks.I. INTRODUCTION Speech recognition in noisy environments is a difficult task. There have been a range of solutions proposed to this problem [1], [2], [3]. One approach that has been successfully applied in a range of tasks is model-based compensation. These schemes include Vector Taylor Series (VTS), [1], and Joint Uncertainty Decoding (JUD), [4]. Here a "clean" acoustic model is adapted to be representative of a model trained in the target acoustic condition. To apply these approaches it is necessary to estimate a background noise model and, using a mismatch function that represents the impact of noise on the clean speech, combine this with the clean model parameters. Schemes have previously been proposed that allow the noise model parameters to be robustly trained using Maximum Likelihood (ML) estimation [3], [5] and will not be discussed in this paper. However, it is not always possible to directly train clean model parameters. Current state-of-the-art speech recognition systems are trained on large amounts of speech data, typically collected in a range of acoustic conditions. It is also expected that collecting data in conditions related to the actual target application conditions should improve performance.To address this problem adaptive training has been proposed [5], [6], [7], [8]. These schemes make use of adaptation/compensation transformations during training. The aim is to train a canonical model removing any dependence on speaker or noise condition. Originally proposed to account for the differences between speakers in the training data [6], these schemes have more recently been applied to situations where there are large variations in the background noise [5], [7]. Model-based compensation schemes have been used [5],

show abstract

Maximum likelihood and minimum classification error factor analysis for automatic speech recognition

Cited by 52 publications

References 23 publications

Signal Modeling and Classification Using a Robust Latent Space Model Based on $t$ Distributions

Signal Modeling and Classification Using a Robust Latent Space Model Based on $t$ Distributions

The Application of Hidden Markov Models in Speech Recognition

Discriminative adaptive training with VTS and JUD

Contact Info

Product

Resources

About