Preprint · 2019 · Open access

PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch

Liang Lu, Xiong Xiao, Zhuo Chen, Yifan Gong

arXiv (Cornell University) · Published 12 July 2019 · DOI 10.48550/arxiv.1907.05955

Free PDFView at the publisherCite this paper

In brief

“PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch” is a 2019 preprint by Liang Lu and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 18 citations as of 16 November 2026. It is open access under a public domain licence: the full text is free to read at arXiv (Cornell University).

Citations
18
Most cited in
2021 (6)
References
12
Authors
4

Abstract

We introduce PyKaldi2 speech recognition toolkit implemented based on Kaldi and PyTorch. While similar toolkits are available built on top of the two, a key feature of PyKaldi2 is sequence training with criteria such as MMI, sMBR and MPE. In particular, we implemented the sequence training module with on-the-fly lattice generation during model training in order to simplify the training pipeline. To address the challenging acoustic environments in real applications, PyKaldi2 also supports on-the-fly noise and reverberation simulation to improve the model robustness. With this feature, it is possible to backpropogate the gradients from the sequence-level loss to the front-end feature extraction module, which, hopefully, can foster more research in the direction of joint front-end and backend learning. We performed benchmark experiments on Librispeech, and show that PyKaldi2 can achieve reasonable recognition accuracy. The toolkit is released under the MIT license.

Cite this paper

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

APA 7

Lu, L., Xiao, X., Chen, Z., & Gong, Y. (2019). PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1907.05955

MLA 9

Lu, Liang, et al. “PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch.” arXiv (Cornell University), 2019. https://doi.org/10.48550/arxiv.1907.05955.

Chicago

Lu, Liang, Xiong Xiao, Zhuo Chen, and Yifan Gong. 2019. “PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1907.05955.

Harvard

Lu, L. et al. (2019) ‘PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch’, arXiv (Cornell University). doi:10.48550/arxiv.1907.05955.

IEEE

L. Lu, X. Xiao, Z. Chen, and Y. Gong, “PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch,” arXiv (Cornell University), 2019, doi: 10.48550/arxiv.1907.05955.

BibTeX

@misc{lu2019pykaldi,
  title     = {{PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch}},
  author    = {Lu, Liang and Xiao, Xiong and Chen, Zhuo and Gong, Yifan},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  doi       = {10.48550/arxiv.1907.05955},
  url       = {https://doi.org/10.48550/arxiv.1907.05955}
}

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

Citations by year

YearCitationsShare of the best year
201911
202044
202166
202233
202311
202411
202511
202611

Topic and keywords

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

  • Kaldi
  • PyTorch
  • maximum mutual information
  • maximum a posteriori estimation
  • noise simulation
  • reverberation simulation
  • LibriSpeech

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?

Lu, L., Xiao, X., Chen, Z., & Gong, Y. (2019). PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1907.05955

How many times has this paper been cited?

18 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 arXiv (Cornell University).

Who wrote this paper?

Liang Lu, Xiong Xiao, Zhuo Chen, Yifan Gong.

What is the DOI of this paper?

10.48550/arxiv.1907.05955. The permanent link is https://doi.org/10.48550/arxiv.1907.05955.

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.