EXTENDED VTS FOR NOISE-ROBUST SPEECH RECOGNITION

EXTENDED VTS FOR NOISE-ROBUST SPEECH RECOGNITION

Cached

Download Links

by R. C. Van Dalen , M. J. F. Gales

Citations:

BibTeX

@MISC{Dalen_extendedvts,
    author = {R. C. Van Dalen and M. J. F. Gales},
    title = {EXTENDED VTS FOR NOISE-ROBUST SPEECH RECOGNITION},
    year = {}
}

Bookmark

OpenURL

Abstract

Model compensation is a standard way of improving speech recognisers’ robustness to noise. Currently popular schemes are based on vector Taylor series (VTS) compensation. They often use the continuous time approximation to compensate dynamic parameters. In this paper, the accuracy of dynamic parameter compensation is improved by representing the dynamic features as a linear transformation of a window of static features. A modified version of VTS compensation is applied to the distribution of the window of static features and, importantly, their correlations. These compensated distributions are then transformed to standard static and dynamic distributions. The proposed scheme outperformed the standard VTS scheme by about 10 % relative. Index Terms — Speech recognition, acoustic noise, robustness 1.

Citations

227	The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions - Pearce, Hirsch - 2000
166	Unscented filtering and nonlinear estimation - Julier, Uhlmann - 2004
145	Environmental robustness in automatic speech recognition - Acero, Stern - 1990
136	Speaker-independent isolated word recognition using dynamic features of speech spectrum - Furui - 1986
100	The darpa 1000-word resource management database for contin 101 uous speech recognition - Price, Fisher, et al. - 1988
72	Speech recognition in noisy environments - Moreno - 1996
65	Model-based techniques for noise robust speech recognition - Gales - 1995
49	HMM adaptation using vector Taylor series for noisy speech recognition - Acero, Deng, et al.
48	Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems - Varga, Steeneken - 1993
26	Uncertainty decoding for noise robust speech recognition - Liao - 2007
23	Joint uncertainty decoding for robust large vocabulary speech recognition - Liao, Gales - 2006
22	Speech recognition in noisy environments using first-order vector Taylor series - Kim, Un, et al. - 1998
18	The HTK Book (for HTK Version 3.4 - YOUNG, EVERMAN - 2009
15	High-performance HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series - Li, Yu, et al.
15	Adaptive training with joint uncertainty decoding for robust recognition of noisy data - Liao, Gales
14	Predictive linear transforms for noise robust speech recognition - Gales, Dalen - 2007
13	Robust speech recognition in noise - performance of the IBM continuous speech recognizer on the ARPA noise spoke task - Gopinath, Gales, et al. - 1995
8	Noise adaptive training using a vector Taylor series approach for noise robust automatic speech recognition - Kalinli, Seltzer, et al.
8	Vector Taylor series based joint uncertainty decoding - Xu, Rigazio, et al. - 2006
5	Bayesian feature enhancement using a mixture of unscented transformations for uncertainty decoding of noisy speech - Shinohara, Akamine - 2009
4	Covariance Modelling for Noise Robust Speech Recognition - Dalen, Gales - 2008
3	Statistical adaptation of acoustic models to noise conditions for robust speech recognition - Torre, Fohr, et al.