An overview of discriminative training for speech recognition

An overview of discriminative training for speech recognition

Cached

Download Links

[www.keithv.com]

by Keith Vertanen

Citations:

1 - 0 self

BibTeX

@TECHREPORT{Vertanen_anoverview,
    author = {Keith Vertanen},
    title = {An overview of discriminative training for speech recognition},
    institution = {},
    year = {}
}

Bookmark

OpenURL

Abstract

This paper gives an overview of discriminative training as it pertains to the speech recognition problem. The basic theory of discriminative training will be discussed and an explanation of maximum mutual information (MMI) given. Common problems inherent to discriminative training will be explored as well as practicalities associated with implementing discriminative training for large vocabulary recognition. Alternatives to the MMI objective function such as minimum word error (MWE) and minimum phone error (MPE) will be discussed. The application of discriminative techniques for adaptation will be described. Finally, possible future avenues of research will be given. 1.

Citations

440	Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models - Leggetter, Woodland - 1995
125	Minimum Phone Error and I-smoothing for Improved Discriminative Training - Povey, Woodland
106	A compact model for speaker adaptive training - Anastasakos, McDonough, et al.
102	Minimum classification error rate methods for speech recognition - Juang, Hou, et al. - 1997
77	An inequality for rational functions with applications to some statistical estimation problems - Gopalakrishnan, Kanevsky, et al. - 1991
77	Large scale discriminative training of hidden Markov models for speech recognition - Woodland, Povey - 2002
60	The acoustic-modelling problem in automatic speech recognition - Brown - 1987
58	Large scale discriminative training for speech recognition - Woodland, Povey
36	An improved mmie training algorithm for speaker-independent, small vocabulary, continuous speech recognition - Normandin, Morgera - 1991
33	MMI Training for Continuous Phoneme Recognition on the TIMIT Database - Kapadia, Valtchev, et al. - 1993
33	Hidden Markov Models, Maximum Mutual Information Estimation and the Speech Recognition Problem - Normandin - 1991
22	On a model-robust training method for speech recognition - Nádas, Nahamoo, et al. - 1988
20	Discriminative training of language models for speech recognition - Kuo, Fosle-Lussier, et al. - 2002
19	A generalization of the Baum algorithm to rational objective functions - Gopalakrishnan, Kanevsky, et al. - 1989
19	Maximum Mutual Information estimation of HMM parameters for continuous speech recognition using the N-best algorithm - Chow - 1990
18	Discriminative Methods for HMM-based Speech Recognition - Valtchev - 1995
17	MMIE training for large vocabulary continuous speech recognition - Normandin, Lacouture, et al. - 1994
16	Phonetic recognition using hidden Markov models and maximum mutual information training - Merialdo - 1988
14	Discriminative Training of Hidden Markov Models - Kapadia - 1998
13	Discriminative linear transforms for speaker adaptation - Uebel, Woodland - 2001
11	Optimal splitting of HMM gaussian mixture components with mmie training - Normandin - 1995
7	Interdependence of language models and discriminative training - Schlüter, Müller, et al.
1	Frame Discrimination of HMMs for Large Vocabulary Speech Recognition - Povey, Woodland - 2000