Kaldi (software)

Kaldi
Developer(s) Daniel Povey and others
Stable release
Revision 3122 / October 2013 (2013-10)
Written in C++
Operating system Unix systems (GNU/Linux, BSD, OSX 10.{8,9} etc.), Windows (via Cygwin)
Type Speech recognition
License Apache License v.2[1]
Website kaldi-asr.org

Kaldi is a speech recognition toolkit, freely available under the Apache License.

Kaldi aims to provide software that is flexible and extensible.[2] It supports linear transforms, MMI, boosted MMI and MCE discriminative training, feature-space discriminative training, and deep neural networks.[3]

Kaldi has been incorporated as part of the CHiME Speech Separation and Recognition Challenge over several successive events.[4][5][6] The software was initially developed as part of a 2009 workshop at Johns Hopkins University.[7]

See also

References

  1. ↑ "Kaldi: Legal stuff". kaldi-asr.org.
  2. ↑ "Kaldi: About the Kaldi project". kaldi-asr.org.
  3. ↑ "Kaldi: Deep Neural Networks in Kaldi". kaldi-asr.org.
  4. ↑ "The 4th CHiME Speech Separation and Recognition Challenge". Retrieved 15 February 2017.
  5. ↑ "The 3rd CHiME Speech Separation and Recognition Challenge". Retrieved 15 February 2017.
  6. ↑ Emmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, Francesco Nesta, et al.. The second 'CHiME' Speech Separation and Recognition Challenge: Datasets, tasks and baselines. ICASSP - 38th International Conference on Acoustics, Speech, and Signal Processing - 2013, May 2013, Vancouver, Canada. pp.126-130, 2013.
  7. ↑ "History of the Kaldi project". Retrieved 26 July 2017.


This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.