swMATH ID: 39131
Software Authors: Y. Wang, T. Chen, H. Xu, S. Ding, H. Lv, Y. Shao, N. Peng, L. Xie, S. Watanabe, S. Khudanpur
Description: Espresso: A fast end-to-end neural speech recognition toolkit. 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)
Homepage: https://arxiv.org/abs/1909.08723
Source Code:  https://github.com/freewym/espresso
Dependencies: Python
Keywords: arXiv_cs.CL; Sound; arXiv_cs.SD; Audio; Speech Processing; arXiv_eess.ASM; speech recognition toolkit; Python
Related Software: Python; LibriSpeech; PyTorch; fairseq; PyTorch-Kaldi; k2; Libri-Light; wav2vec; Asteroid; NeMo; ESPnet; Kaldi; TensorFlow; SpeechBrain; LibROSA; torchaudio; Lingvo; VoxPopuli; ContextNet; SentencePiece
Cited in: 0 Publications