SRILM - an extensible language modeling toolkit

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]  Renato De Mori,et al.  A Cache-Based Natural Language Model for Speech Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Frederick Jelinek,et al.  Up from trigrams! - the struggle for improved language models , 1991, EUROSPEECH.

[3]  Robert L. Mercer,et al.  Class-Based n-gram Models of Natural Language , 1992, CL.

[4]  Mitch Weintraub,et al.  Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Andreas Stolcke,et al.  Bayesian learning of probabilistic language models , 1994 .

[6]  Mari Ostendorf,et al.  Language Modeling with Sentence-Level Mixtures , 1994, HLT.

[7]  Andreas Stolcke,et al.  Statistical language modeling for speech disfluencies , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[8]  Mitch Weintraub,et al.  Explicit word error minimization in n-best list rescoring , 1997, EUROSPEECH.

[9]  Jonathan G. Fiscus,et al.  A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[10]  Andreas Stolcke.  Modeling linguistic segment and turn boundaries for n-best rescoring of spontaneous speech , 1997, EUROSPEECH.

[11]  Ronald Rosenfeld,et al.  Statistical language modeling using the CMU-cambridge toolkit , 1997, EUROSPEECH.

[12]  George Zavaliagkos,et al.  Sub-sentence discourse models for conversational speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[13]  Gökhan Tür,et al.  Modeling the prosody of hidden events for improved word recognition , 1999, EUROSPEECH.

[14]  Stanley F. Chen,et al.  An empirical study of smoothing techniques for language modeling , 1999 .

[15]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[16]  Andreas Stolcke,et al.  THE SRI MARCH 2000 HUB-5 CONVERSATIONAL SPEECH TRANSCRIPTION SYSTEM , 2000 .

[17]  Andreas Stolcke,et al.  Entropy-based Pruning of Backoff Language Models , 2000, ArXiv.

[18]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[19]  R. Rosenfeld,et al.  Two decades of statistical language modeling: where do we go from here? , 2000, Proceedings of the IEEE.

[20]  Andreas Stolcke,et al.  Finding consensus in speech recognition: word error minimization and other applications of confusion networks , 2000, Comput. Speech Lang..

[21]  Wen Wang,et al.  Rescoring effectiveness of language models using different levels of knowledge and their integration , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.