PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch

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.

arXiv comment5 pages, 2 figures, submitted to ICASSP 2020

References in corpus (2)

• Horovod: fast and easy distributed deep learning in TensorFlow
• A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models

Cited by in corpus (6)

• Continuous speech separation: dataset and analysis
• Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
• A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models
• Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
• PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
• Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR