ESPnet: End-to-End Speech Processing Toolkit

By Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Yalta, Jahn Heymann, Matthew Wiesner, Nanxin Chen and 2 more. 2018

1,730 citations recorded by the source corpus.

This paper introduces a new open source platform for end-to-end speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.

Subfields: Artificial Intelligence, Speech & Audio, ML Systems & Hardware, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jinyu Li
  2. Shinji Watanabe
  3. Yoshua Bengio
  4. Jianfeng Gao
  5. Mohit Bansal
  6. Furu Wei
  7. Luke S. Zettlemoyer
  8. James R. Glass

In Speech & Audio

  1. Shinji Watanabe
  2. Jinyu Li
  3. Wei-Ning Hsu
  4. Alexei Baevski
  5. Gabriel Synnaeve
  6. Abdel-rahman Mohamed
  7. Yu Zhang
  8. Michael Auli

In ML Systems & Hardware

  1. Shinji Watanabe
  2. Nima Mesgarani
  3. Yoshua Bengio
  4. Michael Auli
  5. Kilian Q. Weinberger
  6. Adam Polyak
  7. Karen Livescu
  8. Marc Tommasi

In Signal Processing

  1. Shinji Watanabe
  2. Jinyu Li
  3. Dong Yu
  4. Wei-Ning Hsu
  5. Junichi Yamagishi
  6. Hung-yi Lee
  7. James R. Glass
  8. Xu Tan

Citations in the corpus