English

PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch

Computation and Language 2019-10-25 v3 Audio and Speech Processing

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.

Keywords

Cite

@article{arxiv.1907.05955,
  title  = {PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch},
  author = {Liang Lu and Xiong Xiao and Zhuo Chen and Yifan Gong},
  journal= {arXiv preprint arXiv:1907.05955},
  year   = {2019}
}

Comments

5 pages, 2 figures, submitted to ICASSP 2020

R2 v1 2026-06-23T10:20:01.120Z