Issues with uncertainty decoding for noise robust automatic speech recognition

Liao, Hank; Gales, Mark J. F.

doi:10.1016/j.specom.2007.10.004

Cited by 85 publications

(148 citation statements)

References 21 publications

Supporting

Mentioning

146

Contrasting

Order By: Relevance

“…A number of possible forms have been examined in the literature. In this work the first-order VTS scheme described in (Liao and Gales, 2006) is used. A brief summary of the scheme is given here.…”

Section: Vector Taylor Series Compensationmentioning

confidence: 99%

“…This is the form used in (Liao and Gales, 2006; as it was found to outperform γ = 2. It is also consistent with the results in (Li et al, 2007) where α = 1 yielded the majority of the gains over the baseline α = 0, though additional gains were obtained using α = 2.5.…”

Section: Mismatch Function Optimisationmentioning

confidence: 99%

“…In this work Vector Taylor Series (VTS) (Moreno, 1996) compensation using noise model parameters estimated on the test data (Liao and Gales, 2006) is implemented. In addition to a brief description of VTS modelbased compensation, a discussion of recent research for improved performance by optimising the mismatch function is also included (Li et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discriminative classifiers with adaptive kernels for noise robust speech recognition

Gales

Flego

2010

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

Discriminative classifiers are a popular approach to solving classification problems. However one of the problems with these approaches, in particular kernel based classifiers such as Support Vector Machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. This paper describes a scheme for overcoming this problem for speech recognition in noise by adapting the kernel rather than the SVM decision boundary. Generative kernels, defined using generative models, are one type of kernel that allows SVMs to handle sequence data. By compensating the parameters of the generative models for each noise condition noise-specific generative kernels can be obtained. These can be used to train a noiseindependent SVM on a range of noise conditions, which can then be used with a test-set noise kernel for classification. The noise-specific kernels used in this paper are based on Vector Taylor Series (VTS) model-based compensation. VTS allows all the model parameters to be compensated and the background noise to be estimated in a maximum likelihood fashion. A brief discussion of VTS, and the optimisation of the mismatch function representing the impact of noise on the clean speech, is also included. Experiments using these VTS-based test-set noise kernels were run on the AURORA 2 continuous digit task. The proposed SVM rescoring scheme yields large gains in performance over the VTS compensated models.

show abstract

Section: Vector Taylor Series Compensationmentioning

confidence: 99%

Section: Mismatch Function Optimisationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminative classifiers with adaptive kernels for noise robust speech recognition

Gales

Flego

2010

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

show abstract

“…Both VTS and JUD can be described in terms of a model based on the joint distribution of the clean speech and the corrupted speech [4]. Initially JUD will be described.…”

Section: A Vts and Judmentioning

confidence: 99%

“…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.…”

mentioning

confidence: 99%

Discriminative adaptive training with VTS and JUD

Flego

Gales

2009

2009 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

Self Cite

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

Speech‐Recognition Overview

Gold

Morgan

Ellis

2011

Speech and Audio Signal Processing

View full text Add to dashboard Cite

Automatic speech recognition is critical in natural human-centric interfaces for ambient intelligence. The performance of an automatic speech recognition system, however, degrades drastically when there is a mismatch between training and testing conditions. The aim of robust speech recognition is to overcome the mismatch problem so the result is a moderate and graceful degradation in recognition performance. In this chapter, we provide a brief overview of an automatic speech recognition system, describe sources of speech variability that cause mismatch between training and testing, and discuss some of the current techniques to achieve robust speech recognition.

show abstract

Issues with uncertainty decoding for noise robust automatic speech recognition

Cited by 85 publications

References 21 publications

Discriminative classifiers with adaptive kernels for noise robust speech recognition

Discriminative classifiers with adaptive kernels for noise robust speech recognition

Discriminative adaptive training with VTS and JUD

Speech‐Recognition Overview

Contact Info

Product

Resources

About