Mixtures of Bayesian Joint Factor Analyzers for Noise Robust Automatic Speech Recognition

被引：0

作者：

Cui, Xiaodong ^{[1
]}

Goel, Vaibhava ^{[1
]}

Kingsbury, Brian ^{[1
]}

机构：

[1] IBM T J Watson Res Ctr, Yorktown Hts, NY 10598 USA

来源：

14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5 | 2013年

关键词：

Bayesian joint factor analysis; automatic relevance determination; relevance vector machine; noise robustness; LVCSR; SPEAKER; VARIABILITY;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper investigates a noise robust approach to automatic speech recognition based on a mixture of Bayesian joint factor analyzers. In this approach, noisy features are modeled by two joint groups of factors accounting for speaker and noise variabilities which are estimated by clean and noisy speech respectively. The factors form an overcomplete dictionary with a redundant representation. Automatic relevance determination (ARD) is carried out by the relevance vector machine (RVM) where sparsity-promoting priors are applied on two factor loading matrices. Experiments on large vocabulary continuous speech recognition (LVCSR) tasks show good improvements by this approach.

引用

页码：3011 / 3015

页数：5

共 50 条

[41] A MODULATION FEATURE SET FOR ROBUST AUTOMATIC SPEECH RECOGNITION IN ADDITIVE NOISE AND REVERBERATION
Liu, Xiaoyu
Sadeghian, Roozbeh
Zahorian, Stephen A.
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5230 - 5234
[42] Joint Tracking of Clean Speech and Noise Using HMMs and Particle Filters for Robust Speech Recognition
Mushtaq, Aleem
Lee, Chin-Hui
2012 CONFERENCE RECORD OF THE FORTY SIXTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS (ASILOMAR), 2012, : 1618 - 1622
[43] JOINT UNCERTAINTY DECODING WITH THE SECOND ORDER APPROXIMATION FOR NOISE ROBUST SPEECH RECOGNITION
Xu, Haitian
Chin, K. K.
2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 3841 - 3844
[44] Comparison of Estimation Techniques in Joint Uncertainty Decoding for Noise Robust Speech Recognition
Xu, Haitian
Chin, K. K.
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2363 - 2366
[45] Noise robust automatic speech recognition with adaptive quantile based noise estimation and speech band emphasizing filter bank
Bonde, CS
Graversen, C
Gregersen, AG
Ngo, KH
Normark, K
Purup, M
Thorsen, T
Lindberg, B
NONLINEAR ANALYSES AND ALGORITHMS FOR SPEECH PROCESSING, 2005, 3817 : 291 - 302
[46] Dynamic Bayesian networks for automatic speech recognition
Deviren, M
EIGHTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-02)/FOURTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-02), PROCEEDINGS, 2002, : 981 - 981
[47] Overrating Bayesian mixtures of factor analyzers with an unknown number of components
Papastamoulis, Panagiotis
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2018, 124 : 220 - 234
[48] Multi-Channel Speech Enhancement and Amplitude Modulation Analysis for Noise Robust Automatic Speech Recognition
Moritz, Niko
Adiloglu, Kamil
Anemueller, Joern
Goetze, Stefan
Kollmeier, Birger
COMPUTER SPEECH AND LANGUAGE, 2017, 46 : 558 - 573
[49] Knowledge Distillation-Based Training of Speech Enhancement for Noise-Robust Automatic Speech Recognition
Woo Lee, Geon
Kook Kim, Hong
Kong, Duk-Jo
IEEE ACCESS, 2024, 12 : 72707 - 72720
[50] Noise suppression based on wavelet packet decomposition and quantile noise estimation for robust automatic speech recognition
Rank, Erhard
Van Pham, Tuan
Kubin, Gernot
2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 477 - 480

← 1 2 3 4 5 →