Generation and Combination of Complementary Systems for Automatic Speech Recognition

Generation and Combination of Complementary Systems for Automatic Speech Recognition (2008)

Cached

Download Links

by Catherine Breslin

BibTeX

@MISC{Breslin08generationand,
    author = {Catherine Breslin},
    title = {Generation and Combination of Complementary Systems for Automatic Speech Recognition},
    year = {2008}
}

Bookmark

OpenURL

Abstract

It has been found that using a combination of systems for large vocabulary continuous speech recognition (LVCSR) can outperform the use of a single system. For the combination to yield gains, the individual models must be complementary, i.e. they must make different errors. Previous work in ASR has mainly relied on an ad-hoc approach to finding complementary systems. Multiple systems are built, and those that perform well in combination are selected. The multiple diverse systems can be built in many ways, including the use of different frontends, injecting randomness, altering the model topology or using different training

Citations

6696	The Nature of Statistical Learning Theory - Vapnik - 1995
6232	Maximum likelihood from incomplete data via the em algorithm - Dempster, Laird, et al. - 1977
1998	Bagging predictors - Breiman - 1996
1714	Schapire R: A decision-theoretic generalization of online learning and an application to boosting - Freund - 1997
1325	Experiments with a new boosting algorithm - Freund, Schapire - 1996
851	Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady 10: 707–710 - Levenshtein - 1966
809	On Information and Sufficiency - Kullback, RA - 1951
785	Random forests - Breiman - 2001
759	Information Theory, Inference and Learning Algorithms - Mackay - 2003
726	The EM Algorithm and Extensions - McLachlan, Krishnan - 1997
554	The strenght of weak learnability - Schapire - 1990
550	Comparison of parametric representations of monosyllabic word recognition in continuously spoken sentences - Davis, Mermelstein - 1980
443	Perceptual linear predictive (PLP) analysis of speech - Hermansky - 1990
375	Factorial hidden markov models - Ghahramani, Jordan - 1997
372	Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains - Gauvain, Lee - 1994
364	An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting and randomization - Dietterich
353	Training products of experts by minimizing contrastive divergence - Hinton
334	Improving generalization with active learning - Cohn, Atlas, et al. - 1994
287	Objective criteria for the evaluation of clustering methods - Rand - 1971
275	Maximum likelihood linear transformations for HMMbased speech recognition - Gales - 1998
239	A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER - Fiscus - 1997
173	An inequality with applications to statistical estimation for probabilistic functions of a Markov process and to models for ecology - Baum, Eagon - 1967
156	Some statistical issues in the comparison of speech recognition algorithms - Gillick, Cox - 1989
146	Semi-tied covariance matrices for hidden Markov models - Gales - 1999
132	Hidden Markov model decomposition of speech and noise - Varga, Moore - 1990
125	Minimum Phone Error and I-smoothing for Improved Discriminative Training - Povey, Woodland
123	R.: Maximum mutual information estimation of hidden Markov model parameters for speech recognition - Bahl, Brown, et al. - 2000
112	Products of experts - Hinton - 1999
106	A compact model for speaker adaptive training - Anastasakos, McDonough, et al.
106	A new ASR approach based on independent processing and recombination of partial frequency bands - Bourlard, Dupont - 1996
101	Speech recognition by machines and humans - Lippmann - 1997
96	Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models. Computer Speech and Language - Legetter, Woodland - 1995
93	The use of context in large vocabulary speech recognition - Odell - 1995
89	Finding Consensus AmongWords: Lattice-Based Word Error Minimization - Mangu, Brill, et al.
77	Large scale discriminative training of hidden Markov models for speech recognition - Woodland, Povey - 2002
71	Discriminative Training for Large Vocabulary Speech Recognition - Povey - 2004
70	Confidence measures for large vocabulary continuous speech recognition - Wessel, Schlüter, et al. - 2001
66	Investigation of Silicon-Auditory Models and Generalization of Linear Discriminant Analysis for Improved Speech Recognition - Kumar - 1997
64	Buckwalter arabic morphological analyzer, version 2.0 - Buckwalter - 2004
63	X: Word graph algorithm for large vocabulary continuous speech recognition. Computer Speech and Language - Ortmanns, Ney, et al. - 1997
60	Explicit word error minimization in N-Best list rescoring - Stolcke, Konig, et al. - 1997
59	Ensemble methods - Dietterich
54	On contrastive divergence learning - Carreira-Perpiñán, Hinton - 2005
52	Estimating confidence using word lattices - Kemp, Schaaf - 1997
52	fMPE: Discriminatively trained features for speech recognition - Povey, Kingsbury, et al. - 2005
51	The Generation and Use of Regression Class Trees for mllr Adaptation - Gales - 1996
47	Discriminative Model Combination - Beyerlein - 1998
42	Minimum Bayes-risk automatic speech recognition - Goel, Byrne - 2003
41	Neural-network based measures of confidence for word recognition - Weintraub - 1997
34	Lightly supervised and unsupervised acoustic model training - Lamel, Gauvain, et al. - 2002