Paper · 2024 · Open access

Kaldi Speech Recognition Toolkit

Daniel Povey

Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Published 1 January 2024 · DOI 10.57702/jb3fvbn9

Free PDFView at the publisherCite this paper

In brief

“Kaldi Speech Recognition Toolkit” is a 2024 paper by Daniel Povey, published in Infoscience (Ecole Polytechnique Fédérale de Lausanne). OpenAlex counts 5,270 citations as of 16 November 2026, which puts it in the top 5% of works published in 2024 by citations. It is open access: the full text is free to read at Infoscience (Ecole Polytechnique Fédérale de Lausanne).

Citations
5,270
Most cited in
2019 (700)
Field-weighted impact
29.66
References
15
Authors
1

Abstract

—We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available OpenFst), together with detailed documentation and scripts for building complete recognition systems. Kaldi is written is C++, and the core library supports modeling of arbitrary phonetic-context sizes, acoustic modeling with subspace Gaussian mixture models (SGMM) as well as standard Gaussian mixture models, together with all commonly used linear and affine transforms. Kaldi is released under the Apache License v2.0, which is highly nonrestrictive, making it suitable for a wide community of users. I.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Povey, D. (2024). Kaldi Speech Recognition Toolkit. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.57702/jb3fvbn9

MLA 9

Povey, Daniel. “Kaldi Speech Recognition Toolkit.” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2024. https://doi.org/10.57702/jb3fvbn9.

Chicago

Povey, Daniel. 2024. “Kaldi Speech Recognition Toolkit.” Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.57702/jb3fvbn9.

Harvard

Povey, D. (2024) ‘Kaldi Speech Recognition Toolkit’, Infoscience (Ecole Polytechnique Fédérale de Lausanne). doi:10.57702/jb3fvbn9.

IEEE

D. Povey, “Kaldi Speech Recognition Toolkit,” Infoscience (Ecole Polytechnique Fédérale de Lausanne), 2024, doi: 10.57702/jb3fvbn9.

BibTeX

@article{povey2024kaldi,
  title     = {{Kaldi Speech Recognition Toolkit}},
  author    = {Povey, Daniel},
  journal   = {Infoscience (Ecole Polytechnique Fédérale de Lausanne)},
  year      = {2024},
  doi       = {10.57702/jb3fvbn9},
  url       = {https://doi.org/10.57702/jb3fvbn9}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
2017512512
2018629629
2019700700
2020671671
2021677677
2022402402
2023296296
2024205205
20257878
202622

Its field-weighted citation impact is 29.66: it has been cited 29.66 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis

  • Kaldi
  • finite-state transducers
  • acoustic modeling
  • subspace Gaussian mixture models
  • Gaussian mixture model
  • linear operators
  • affine transformation
  • phonetic context

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Povey, D. (2024). Kaldi Speech Recognition Toolkit. Infoscience (Ecole Polytechnique Fédérale de Lausanne). https://doi.org/10.57702/jb3fvbn9

How many times has this paper been cited?

5,270 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Infoscience (Ecole Polytechnique Fédérale de Lausanne).

Who wrote this paper?

Daniel Povey.

What is the DOI of this paper?

10.57702/jb3fvbn9. The permanent link is https://doi.org/10.57702/jb3fvbn9.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.