English

Learning Shared Encoding Representation for End-to-End Speech Recognition Models

Audio and Speech Processing 2019-04-04 v1 Machine Learning Sound

Abstract

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereby, we train a deep attention-based end-to-end model with 10 long short-term memory (LSTM) layers of encoder which produces 12.2\% and 22.6\% word-error-rate on Switchboard and CallHome subsets of the Hub5 2000 evaluation.

Keywords

Cite

@article{arxiv.1904.02147,
  title  = {Learning Shared Encoding Representation for End-to-End Speech Recognition Models},
  author = {Thai-Son Nguyen and Sebastian Stueker and Alex Waibel},
  journal= {arXiv preprint arXiv:1904.02147},
  year   = {2019}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1902.01951

R2 v1 2026-06-23T08:28:28.372Z