Papperoni

2002

Srilm - An Extensible Language Modeling Toolkit

Andreas Stolcke

Open PDF Google Scholar

citations

Cite Score

76

AI summary

This paper introduces the SRI Language Modeling Toolkit (SRILM), a C++ library and set of tools for building and evaluating statistical language models based on N-gram statistics. It supports speech recognition and other applications, offering a programming interface, extensible LM classes, and comprehensive functionality for tagging and N-best rescoring.

Main Contributions

Introduces the SRI Language Modeling Toolkit (SRILM), a collection of C++ libraries, programs, and scripts for statistical language modeling.
Offers a programming interface and an extensible set of LM classes.
Provides several non-standard LM types.
Includes comprehensive functionality beyond language modeling, such as tagging and N-best rescoring.
Discusses the design philosophy and key implementation choices in SRILM, emphasizing rapid prototyping, reusability, and combinability.

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.

Citation Graph

Loading graph...

References [23]

Sort:

Filter:

[1]An Empirical Study of Smoothing Techniques for Language Modeling

S. F. Chen, J. Goodman - 1998

13 papers in library cite

[2]Class-Based N-Gram Models of Natural Language

P. F. Brown, P. V. Desouza, R. L. Mercer, Vincent J. Della Pietra, J. C. Lai - 1992

12 papers in library cite

[3]A Cache-Based Natural Language Model for Speech Recognition

R. Kuhn, R. D. Mori - 1990

6 papers in library cite

[4]A Post-Processing System to Yield Reduced Error Word Rates: Recognizer Output Voting Error Reduction (ROVER)

J. G. Fiscus - 1997

2 papers in library cite

[5]Entropy-Based Pruning of Back-Off Language Models

Andreas Stolcke - 1998

2 papers in library cite

[6]Two Decades of Statistical Language Modeling: Where Do We Go From Here?

R. Rosenfeld - 2000

2 papers in library cite

[7]Bayesian Learning of Probabilistic Language Models

Andreas Stolcke - 1994

1 paper in library cites

[8]Explicit Word Error Minimization in N-Best List Rescoring

Andreas Stolcke, Y. Konig, M. Weintraub - 1997

1 paper in library cites

[9]Finding Consensus in Speech Recognition: Word Error Minimization and Other Applications of Confusion Networks

L. Mangu, E. Brill, Andreas Stolcke - 2000

1 paper in library cites

[10]FSM Library—general-Purpose Finite-State Machine Software Tools, Version 3.6

M. Mohri, Fernando Pereira, M. Riley - 1998

1 paper in library cites

[11]Language Modeling With Sentence-Level Mixtures

R. Iyer, M. Ostendorf, J. R. Rohlicek - 1994

1 paper in library cites

[12]Large Vocabulary Dictation Using SRI’s DECIPHER speech Recognition System: Progressive Search Techniques

H. Murveit, J. Butzberger, V. Digalakis, M. Weintraub - 1993

1 paper in library cites

[13]Lattice and Language Model Toolkit Reference Manual

J. J. Odell - 1995

1 paper in library cites

[14]LM95 Project Report: Fast Training and Portability

M. Weintraub, Y. Aksu, S. Dharanipragada, Sanjeev Khudanpur, Hermann Ney, J. Prange, Andreas Stolcke, Frederick Jelinek, E. Shriberg - 1996

1 paper in library cites

[15]Modeling Linguistic Segment and Turn Boundaries for N-Best Rescoring of Spontaneous Speech

Andreas Stolcke, Y. Konig, M. Weintraub - 1997

1 paper in library cites

[16]Modeling the Prosody of Hidden Events for Improved Word Recognition

Andreas Stolcke, E. Shriberg, D. H. T. "ur, G. T. "ur - 1999

1 paper in library cites

[17]Rescoring Effectiveness of Language Models Using Different Levels of Knowledge and Their Integration

Wenyi Wang, Yibo Liu, M. P. Harper - 2002

1 paper in library cites

[18]Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Dan Jurafsky, J. H. Martin - 2000

1 paper in library cites

[19]Statistical Language Modeling for Speech Disfluencies

Andreas Stolcke, E. Shriberg - 1996

1 paper in library cites

[20]Statistical Language Modeling Using the CMU-Cambridge Toolkit

P. Clarkson, R. Rosenfeld - 1997

1 paper in library cites

[21]Sub-Sentence Discourse Models for Conversational Speech Recognition

K. W. Ma, G. Zavaliagkos, M. Meteer - 1998

1 paper in library cites

[22]The SRI March 2000 Hub-5 Conversational Speech Transcription System

Andreas Stolcke, H. Bratt, J. Butzberger, H. Franco, V. R. R. Gadde, M. Plauch'e, C. Richey, E. Shriberg, K. S. "onmez, F. Weng, James Zheng - 2000

1 paper in library cites

[23]Up From Trigrams! The Struggle for Improved Language Models

Frederick Jelinek - 1991

1 paper in library cites

Cited by

13

papers in your library

Cites

0

papers in your library

Read

on July 21, 2025

Toolkit for N-grams. Not too relevant and sounds veeeery simple (sorry for those who implemented it). It's nice to see early implementation of OOP though. The paper is boring and doesn't really say much about the framework, more of a description of how to use the commands and n-gram models.

Tags

Paper Aliases

No aliases