Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
arXiv:1909.08723
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).
arXiv commentAccepted to ASRU 2019
References in corpus (15)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- When Does Label Smoothing Help?
- On Using Monolingual Corpora in Neural Machine Translation
- End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
- wav2letter++: The Fastest Open-source Speech Recognition System
- Transformers with convolutional context for ASR
- Fully Convolutional Speech Recognition
- RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
- Who Needs Words? Lexicon-Free Speech Recognition
Cited by in corpus (6)
- SpeechBrain: A General-Purpose Speech Toolkit
- Adversarial Attacks and Defenses for Speech Recognition Systems
- The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
- Wake Word Detection with Alignment-Free Lattice-Free MMI
- PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
- CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency