• Skip to primary navigation
  • Skip to main content
SRI logo
  • About
    • Press room
    • Our history
  • Expertise
    • Advanced imaging systems
    • Artificial intelligence
    • Biomedical R&D services
    • Biomedical sciences
    • Computer vision
    • Cyber & formal methods
    • Education and learning
    • Innovation strategy and policy
    • National security
    • Ocean & space
    • Quantum
    • QED-C
    • Robotics, sensors & devices
    • Speech & natural language
    • Video test & measurement
  • Ventures
  • NSIC
  • Careers
  • Contact
  • 日本支社
Search
Close
Platform December 25, 2019

SRI Language Modeling toolkit

The SRI Language Modeling (SRILM) toolkit offers tools for building and applying statistical language models for use in speech recognition, statistical tagging and segmentation, and machine translation. The toolkit can be downloaded and used free of charge.


Components

  • A set of C++ class libraries implementing language models, supporting data structures, and miscellaneous utility functions
  • A set of executable programs built on top of the libraries to perform standard tasks such as training LMs and testing them on data, tagging, or segmenting text
  • A collection of miscellaneous scripts facilitating minor related tasks
  • The SRILM toolkit runs on UNIX and Windows platforms. It has been used in a great variety of statistical modeling applications. Others have published extensions to it that add new functionality. The toolkit greatly benefitted from its use and enhancements during workshops sponsored by Johns Hopkins University and Oregon Health and Science University’s Center for Spoken Language Understanding in 1995, 1996, 1997, and 2002.

Applications

The SRILM toolkit is widely used in the research community for tasks requiring statistical language modeling. Examples include:

Speech recognition

  • SRI’s automatic speech recognition engine, DynaSpeak®
  • Freely available recognition systems such as RWTH-ASR, Julius, Sphinx, and LIUM
  • SailAlign, a tool for robust long speech-text alignment

Machine translation

  • Language modeling support for the Moses SMT system and the Joshua hierarchical phrase-based SMT system
  • Cunei machine translation platform
  • Integration with SYSTRAN’s Enterprise Server 7 machine translation product

Tagging and segmentation

  • MorphTagger, an HMM-based part-of-speech tagger for Semitic languages
  • Chinese word segmentation

Document processing

  • Handwriting recognition
  • GiDoc (Gimp-based Interactive transcription of old text DOCuments)

Outside computational linguistics

  • RANKPEP: prediction of MHC-restricted ligands
  • Visualization of uncertainty

Teaching

  • Carnegie Mellon University’s (CMU’s) Advanced Lab Speech Recognition and Understanding
  • CMU’s Machine Translation
  • Center for Spoken Language Understanding’s Automatic Speech Recognition and Hidden Markov Models
  • Mississippi State University’s Fundamentals of Speech Recognition
  • Stanford University’s Speech Recognition and Synthesis
  • University of Washington’s Introduction to Computational Linguistics

IDEs and language bindings

  • Visual Studio
  • Python
  • OCaml

Documentation
The SRILM toolkit is still under development. The documentation is also a work in progress. Best documented are the executable programs, scripts, and file formats, in the form of UNIX-style manual pages. The libraries are documented mostly in the source code.

An overview of what the software can do and its design philosophy can be found in the paper, “SRILM – An Extensible Language Modeling Toolkit”“, in Procedures of the International Conference on Spoken Language Processing, Denver, Colorado, September 2002. A 2011 paper, “SRILM at Sixteen: Update and Outlook”, summarizes updates to SRILM since the 2002 paper.

Get links to other papers and tutorials, and answers to frequently asked questions.

Terms of use
SRI has released the SRILM toolkit mainly because we have received requests for the software from several researchers around the world. There is no guarantee of support. It can be downloaded free of charge under an “open source community license”, meaning that you can use it freely for nonprofit purposes, as long as you share any changes you make with the rest of the user community. For other uses, inquire about commercial licensing opportunities.

Mailing list
Check the mailing list archive for past contributions.

Share this

How can we help?

Once you hit send…

We’ll match your inquiry to the person who can best help you.

Expect a response within 48 hours.

Career call to action image

Make your own mark.

Search jobs

Our work

Case studies

Publications

Timeline of innovation

Areas of expertise

Institute

Leadership

Press room

Media inquiries

Compliance

Careers

Job listings

Contact

SRI Ventures

Our locations

Headquarters

333 Ravenswood Ave
Menlo Park, CA 94025 USA

+1 (650) 859-2000

Subscribe to our newsletter


日本支社
SRI International
  • Contact us
  • Privacy Policy
  • Cookies
  • DMCA
  • Copyright © 2022 SRI International