CAT: CRF-based ASR Toolkit
arXiv:1911.08747
Abstract
In this paper, we present a new open source toolkit for automatic speech recognition (ASR), named CAT (CRF-based ASR Toolkit). A key feature of CAT is discriminative training in the framework of conditional random field (CRF), particularly with connectionist temporal classification (CTC) inspired state topology. CAT contains a full-fledged implementation of CTC-CRF and provides a complete workflow for CRF-based end-to-end speech recognition. Evaluation results on Chinese and English benchmarks such as Switchboard and Aishell show that CAT obtains the state-of-the-art results among existing end-to-end models with less parameters, and is competitive compared with the hybrid DNN-HMM models. Towards flexibility, we show that i-vector based speaker-adapted recognition and latency control mechanism can be explored easily and effectively in CAT. We hope CAT, especially the CRF-based framework and software, will be of broad interest to the community, and can be further explored and improved.
Code released at: https://github.com/thu-spmi/cat
References in corpus (7)
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Sequence Transduction with Recurrent Neural Networks
- Improved training of end-to-end attention models for speech recognition
- Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
- wav2letter++: The Fastest Open-source Speech Recognition System
- Fully Convolutional Speech Recognition
- RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
Cited by in corpus (5)
- Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition
- Non-autoregressive Transformer-based End-to-end ASR using BERT
- PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
- Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
- Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data