# PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch

arXiv: https://arxiv.org/abs/1907.05955 · HTML: https://mlsanity.com/paper/1907.05955/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR](https://mlsanity.com/paper/2102.06816/) (2021)
- [Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System](https://mlsanity.com/paper/2106.09963/) (2021)
- [Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition](https://mlsanity.com/paper/2202.12326/) (2022)
- [Improving multichannel speech enhancement through accurate room-acoustic simulations](https://mlsanity.com/paper/2606.31552/) (2026)
- [ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi](https://mlsanity.com/paper/2104.01384/) (2021)

## Abstract (arXiv)

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.