Assessment of signal subspace based speech enhancement for noise robust speech recognition

Hermus, Kris; Wambacq, Patrick

doi:10.1109/icassp.2004.1326143

Cited by 11 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other commonly used single channel acoustic domain based speech enhancement methods include the Log MMSE STSA estimator [10], Weighted-Euclidean STSA (WE STSA) estimator [11], the β-SA estimator [12] and Weightedβ-SA (Wβ-SA) estimator [13], Wiener filtering [14], and signal subspace methods [19][20][21][22][23]. We refer the interested readers to the related publications to get more acquainted with these methods.…”

Section: Acoustic Domain Based Speech Enhancement Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Mani

Champagne

Zhu

2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

Conventional single-channel speech enhancement methods implement the analysis-modification-synthesis (AMS) framework in the acoustic frequency domain. Recently, it has been shown that the extension of this framework to the modulation domain may result in better noise suppression. However, this conclusion has been reached by relying on a minimum statistics approach for the required noise power spectral density (PSD) estimation.Various noise estimation algorithms have been proposed over the years in the speech and audio processing literature. Among these, the widely used minimum statistics approach is known to introduce a time frame lag in the estimated noise spectrum. This can lead to highly inaccurate PSD estimates when the noise behaviour rapidly changes with time, i.e., non-stationary noise. Speech enhancement methods which employ these inaccurate noise PSD estimates tend to perform poorly in the noise suppression task, and in worst cases, may end up deteriorating the noisy speech signal even further. Noise PSD estimation algorithms using a priori information about the noise statistics have been shown to track non-stationary noise better than the conventional algorithms which rely on the minimum statistics approach.In this thesis, we perform noise suppression in the modulation domain with the noise and speech PSD derived from an estimation scheme which employs the a priori information of various speech and noise types. Specifically, codebooks of gain normalized linear prediction coefficients obtained from training on various speech and noise files are used as the a priori information while performing the estimation of the desired PSD. The PSD estimates derived from this codebook approach are used to obtain a minimum mean square error (MMSE) estimate of the clean speech modulation magnitude spectrum, which is then combined with the phase spectrum of the noisy speech to recover the enhanced speech signal. The enhanced speech signal is subjected to various objective experiments for evaluation. Results of these evaluations indicate improvement in noise suppression with the proposed codebook-based modulation domain approach over competing approaches, particularly in cases of nonstationary noise.ii Sommaire Les méthodes conventionnelles de rehaussement de la paroleà canal unique utilisent une structure d'analyse-modification-synthèse (AMS) dans le domaine fréquentiel. Récemment, il aété démontré que l'utilisation de cette structure dans le domaine de la modulation pourrait offrir une meilleure suppression du bruit. Toutefois, cette conclusion aété obtenue en se basant sur une approcheà statistique minimale pour l'estimation de la densité spectrale de puissance (PSD) du bruit ambiant.Plusieurs algorithmes d'estimation de bruit ontété proposés au fil des ans dans la littérature sur le traitement de la parole. D'ordinaire, les méthodes d'estimation de bruit qui se servent d'une approcheà statistique minimale vont créer un décalage temporel dans l'estimation spectrale du bruit. Ce décalage peut engendrer beaucou...

show abstract

Section: Acoustic Domain Based Speech Enhancement Methodsmentioning

confidence: 99%

“…It aims to estimate the clean speech signal after decomposing the noisy speech signal into so called speech signal and noise subspaces. More sophisticated extensions of the subspace approach have been proposed over the subsequent years [20][21][22][23].…”

Section: Overview Of Single Channel Speech Enhancementmentioning

confidence: 99%

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Mani

Champagne

Zhu

2015

2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

show abstract

“…These methods can be grouped under three categories based on (a) compensation of noise, (b) robust feature extraction and (c) adaptation of models. Methods based on compensation of noise aim to enhance the noisy speech signals before feature extraction (Mokbel and Chollet 1991;Nolazco-Flores and Young 1993;Huang and Zhao 1997;Hermus et al 2000;Hermus and Wambacq 2004;Kris and Patrick 2007). Such methods include spectral subtraction, minimum mean square error (MMSE) and subspace based speech enhancement techniques (Huang and Zhao 1997;Hermus et al 2000;Hermus and Wambacq 2004;Kris and Patrick 2007).…”

Section: Introductionmentioning

confidence: 97%

“…Methods based on compensation of noise aim to enhance the noisy speech signals before feature extraction (Mokbel and Chollet 1991;Nolazco-Flores and Young 1993;Huang and Zhao 1997;Hermus et al 2000;Hermus and Wambacq 2004;Kris and Patrick 2007). Such methods include spectral subtraction, minimum mean square error (MMSE) and subspace based speech enhancement techniques (Huang and Zhao 1997;Hermus et al 2000;Hermus and Wambacq 2004;Kris and Patrick 2007). Methods based on robustness at the feature level are designed in such a way that the proposed features are less sensitive to the noisy degraded conditions (Hermanski et al 1994;Viiki et al 1998;Yu et al 2008;Cui and Alwan 2005;Hilger and Ney 2006;de la Torre et al 2005;Suh et al 2007), e.g, RASTA filter (Hermanski et al 1994), feature normalization (Viiki et al 1998), MMSE based Melfrequency cepstra (Yu et al 2008), and histogram equalization (Hilger and Ney 2006;de la Torre et al 2005;Suh et al 2007) etc.…”

Section: Introductionmentioning

confidence: 97%

Recognition of consonant-vowel (CV) units under background noise using combined temporal and spectral preprocessing

Vuppala

Rao

Chakrabarti

et al. 2011

Int J Speech Technol

View full text Add to dashboard Cite

This paper proposes hybrid classification models and preprocessing methods for enhancing the consonantvowel (CV) recognition in the presence of background noise. Background Noise is one of the major degradation in real-time environments which strongly effects the performance of speech recognition system. In this work, combined temporal and spectral processing (TSP) methods are explored for preprocessing to improve CV recognition performance. Proposed CV recognition method is carried out in two levels to reduce the similarity among large number of CV classes. In the first level vowel category of CV unit will be recognized, and in the second level consonant category will be recognized. At each level complementary evidences from hybrid models consisting of support vector machine (SVM) and hidden Markov models (HMM) are combined for enhancing the recognition performance. Performance of the proposed CV recognition system is evaluated on Telugu A.K. Vuppala ( ) · S. Chakrabarti G. S.

show abstract

“…One important assumption of signal subspace approach is that the largest singular values or Eigen values are from speech and the smallest values are from noise. In [40] several subspace-based methods have been evaluated on noisy speech recognition task.…”

Section: Subspace-based Techniquesmentioning

confidence: 99%

Features and Model Adaptation Techniques for Robust Speech Recognition: A Review

Legoh¹,

Bhattacharjee²,

Tuithung³

2015

CAE

View full text Add to dashboard Cite

In this paper, major speech features used in state-of-the-art technology in speech recognition research are reviewed. Also a brief review of major technological advancements during last few decades and a trend towards development of robust speech recognition system in terms of feature and model adaptation techniques is given. It has been the dream of researchers to develop a machine that recognizes speech and understands natural language like human but the reality is that the performance of the speech recognition system drastically degrades due to various adverse conditions like noise, variability in speaker, channel, device and mismatches in training and testing. This paper may be useful as a tutorial and review on state-of-the-art techniques for feature selection, feature normalization and model adaptation techniques for development of robust speech recognition system.

show abstract

Assessment of signal subspace based speech enhancement for noise robust speech recognition

Cited by 11 publications

References 11 publications

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Speech enhancement in modulation domain using codebook-based speech and noise estimation

Recognition of consonant-vowel (CV) units under background noise using combined temporal and spectral preprocessing

Features and Model Adaptation Techniques for Robust Speech Recognition: A Review

Contact Info

Product

Resources

About