Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Preprint
Abstract
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed training across GPUs and computing nodes, and features various decoding approaches commonly employed in ASR, including look-ahead word-based language model fusion, for which a fast, parallelized decoder is implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard data sets among other end-to-end systems without data augmentation, and is 4--11x faster for decoding than similar systems (e.g. ESPnet).Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition2018
- Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates2018
- Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition2017
- Towards Better Decoding and Language Model Integration in Sequence to Sequence Models2017
- Listen, attend and spell: A neural network for large vocabulary conversational speech recognition2016
- EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding2015