Abstract

SRILM is a collection of C++ libraries, executable programs, and helper scripts designed to allow both production of and experimentation with statistical language models for speech recognition and other applications. SRILM is freely available for noncommercial purposes. The toolkit supports creation and evaluation of a variety of language model types based on N-gram statistics, as well as several related tasks, such as statistical tagging and manipulation of N-best lists and word lattices. This paper summarizes the functionality of the toolkit and discusses its design and implementation, highlighting ease of rapid prototyping, reusability, and combinability of tools. 1.

Citations

631	J: An Empirical Study of Smoothing Techniques for Language Modeling - SF, Goodman - 1996
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
264	Statistical language modeling using the cmucambridge toolkit - Clarkson, Rosenfeld - 1997
239	A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER - Fiscus - 1997
202	Speech and Language Processing – An Introduction to - Jurafsky, Martin - 2009
142	A cache-based natural language model for speech recognition - Kuhn, Mori - 1990
119	Two decades of statistical language modeling: Where do we go from here - Rosenfeld
115	Finding consensus in speech recognition; word error minimization and other applications of confusion networks - Mangu, Brill, et al. - 2000
110	Bayesian Learning of Probabilistic Language Models - Stolcke - 1994
88	Entropy-based pruning of backoff language models - Stolcke - 1998
60	Explicit word error minimization in N-Best list rescoring - Stolcke, Konig, et al. - 1997
52	Statistical language modeling for speech disfluencies - Stolcke, Shriberg - 1996
47	Large-Vocabulary Dictation Using SRI's DECIPHER TM Speech Recognition System: Progressive Search Technique - Murveit, Butzberger, et al. - 1993
28	Up from trigrams! The struggle for improved language models - Jelinek - 1991
27	Modeling the prosody of hidden events for improved word recognition - Stolcke, Shriberg, et al. - 1999
26	The sri march 2000 hub-5 conversational speech transcription system - Stolcke, Bratt, et al.
23	Language modeling with sentence-level mixtures - Iyer, Ostendorf, et al. - 1994
12	Modeling linguistic segment and turn boundaries for Nbest rescoring of spontaneous speech - Stolcke - 1997
8	FSM Library – General-purpose finite-state machine software tools - Mohri, Pereira, et al. - 1998
6	Lm 95 project report. fast training and portability” Language Modeling - Weintraub - 1995
6	Sub-sentence discourse models for conversational speech recognition - Ma, Zavaliagkos, et al. - 1998
6	Rescoring effectiveness of language models using different levels of knowledge and their integration - Wang, Liu, et al. - 2002
6	Class-basedn-gram models of natural language - BROWN, PIETRA, et al. - 1992
2	Lattice and Language Model Toolkit Reference Manual. Entropic Cambridge Research Laboratories - Odell - 1995