Multi-head decoder for end-to-end speech recognition

Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then, they are integrated into a single attention. On the other hand, instead of the integration in the attention level, our proposed method uses multiple decoders for each attention and integrates their outputs to generate a final output. Furthermore, in order to make each head to capture the different modalities, different attention functions are used for each head, leading to the improvement of the recognition performance with an ensemble effect. To evaluate the effectiveness of our proposed method, we conduct an experimental evaluation using Corpus of Spontaneous Japanese. Experimental results demonstrate that our proposed method outperforms the conventional methods such as location-based and multi-head attention models, and that it can capture different speech/linguistic contexts within the attention-based encoder-decoder framework.

Original languageEnglish
Pages (from-to)801-805
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2018-September
DOIs
Publication statusPublished - 2018
Externally publishedYes
Event19th Annual Conference of the International Speech Communication, INTERSPEECH 2018 - Hyderabad, India
Duration: 2018 Sep 22018 Sep 6

Keywords

  • Attention
  • Dynamical neural network
  • End-to-end
  • Speech recognition

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Multi-head decoder for end-to-end speech recognition'. Together they form a unique fingerprint.

Cite this