Abstract

Speech recognition performance is severely affected when the lexical, syntactic, or semantic characteristics of the discourse in the training and recognition tasks differ. The aim of language model adaptation is to exploit specific, albeit limited, knowledge about the recognition task to compensate for this mismatch. More generally, an adaptive language model seeks to maintain an adequate representation of the current task domain under changing conditions involving potential variations in vocabulary, syntax, content, and style. This paper presents an overview of the major approaches proposed to address this issue, and offers some perspectives regarding their comparative merits and associated tradeoffs. Ó 2003 Elsevier B.V. All rights reserved. 1.

Citations

2168	R.A.: Indexing by latent semantic analysis - Deerwester, Dumais, et al. - 1990
464	Inducing Features of Random Fields - Pietra, Pietra, et al. - 1997
375	Probabilistic latent semantic analysis - Hofmann - 1999
355	Generalized Iterative Scaling for Log-Linear Models - Darroch, Ratcliff - 1972
345	A maximum likelihood approach to continuous speech recognition - Bahl, Jelinek - 1983
201	A maximum entropy approach to adaptive statistical language modelling - Rosenfeld - 1996
164	Introduction to the Theory of Statistics - Mood, Graybill, et al. - 1974
131	Recognition and parsing of context-free languages in time n 3 . Information and Control, 10(2):189–208. 42 Full Code for the Deductive Parsing Engine 〈Listing of file infer.pl〉 /*========================================================== Parser Based on a - Younger - 1967
106	Exploiting syntactic structure for language modeling - Chelba, Jelinek - 1998
103	Speech Recognition by Composition of Weighted Finite Automata - Pereira, Riley - 1997
77	Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models - Iyer, Ostendorf - 1996
75	2000. “A Survey of Smoothing Techniques for ME Models - Chen, Rosenfeld
68	Trigger-Based Language Models: a Maximum Entropy Approach - Lau, Rosenfeld, et al. - 1993
67	Language model adaptation using mixtures and an exponentially decaying cache - Clarkson, Robinson - 1997
57	Structured language modeling - Chelba, Jelinek - 2000
54	Exploiting latent semantic information in statistical language modeling - Bellegarda - 2000
54	Tied mixture continuous parameter modeling for speech recognition - Bellegarda - 1990
48	Using story topics for language model adaptation - Seymore, Rosenfeld - 1997
47	Minimization Algorithms for Sequential Transducers - Mohri
44	Language model adaptation using dynamic marginals - Kneser, Peters, et al. - 1997
42	A variable-length category-based n-gram language model - Niesler, Woodland - 1996
40	The Development of an Experimental Discrete Dictation Recognizer - Jelinek - 1985
37	Towards better integration of semantic predictors in statistical language modeling - Coccaro, Jurafsky - 1998
35	Topic-based language models using EM - Gildea, Hofmann - 1999
34	On Automated Language Acquisition - Gorin - 1995
31	Optimizing Lexical and N-gram Coverage via Judicious Use of Linguistic Data - Rosenfeld - 1995
28	On the dynamic adaptation of stochastic language models - Kneser, Steinbiss - 1993
28	Improving trigram language modeling with the world wide web - Zhu, Rosenfeld - 2000
27	A multispan language modeling framework for large vocabulary speech recognition - Bellegarda - 1998
25	Structure and Performance of a Dependency Language Model - Chelba - 1997
25	A whole sentence maximum entropy language model - Rosenfeld - 1997
24	A maximum likelihood model for topic classi cation of broadcast news - Schwartz, Imai, et al. - 1997
23	Language modeling with sentence-level mixtures - Iyer, Ostendorf, et al. - 1994
22	Large vocabulary speech recognition with multispan statistical language models - Bellegarda - 2000
20	Cluster expansions and iterative scaling for maximum entropy language models - Laerty, Suhm - 1996
20	Stochastic Language Adaptation over Time and State in Natural Spoken Dialogue Systems - Riccardi, Gorin - 2000
19	Topic adaptation for language modeling using unnormalized exponential models - Chen, Seymore, et al. - 1998
19	Bayesian estimation methods for n-gram language model adaptation - Federico - 1996
19	The thoughtful elephant – Strategies for spoken dialog systems - Souvignier, Kellner, et al. - 2000
18	Adaptative topic-dependent language modelling using wordbased varigrams - Martin, Liermann, et al. - 1997
16	Just-in-time language modelling - Berger, Miller - 1998
16	On-line learning of language models with word error probability distributions - Gretter, Riccardi - 2001
16	Multilingual stochastic n-gram class language models - Jardino - 1996
15	Phonological parsing in speech recognition - Church - 1987
14	Semantic clustering for adaptive language modeling", ICASSP - Kneser, Peters - 1997
14	Combining nonlocal, syntactic and n-gram dependencies in language modeling - Wu, Khudanpur
13	Language modeling for broadcast news transcription - Adda, Jardino, et al. - 1999
13	Exploiting both local and global constraints for multi-span statistical language modeling - Bellegarda - 1998
13	Putting language into language modeling - Jelinek, Chelba - 1999
12	Language Model Speaker Adaptation - Besling, Meier - 1995