Improving end-to-end speech recognition with pronunciation-assisted sub-word modeling

Hainan Xu, Shuoyang Ding, Shinji Watanabe

Research output: Contribution to journalArticlepeer-review

Abstract

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word segmentation that might lead to erroneous speech recognition output. We propose pronunciation-assisted sub-word modeling (PASM), a sub-word extraction method that leverages the pronunciation information of a word. Experiments show that the proposed method can greatly improve upon the characterbased baseline, and also outperform commonly used byte-pair encoding methods.

Original languageEnglish
JournalUnknown Journal
Publication statusPublished - 2018 Nov 10
Externally publishedYes

Keywords

  • End-to-end models
  • Speech recognition
  • Sub-word modeling

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Improving end-to-end speech recognition with pronunciation-assisted sub-word modeling'. Together they form a unique fingerprint.

Cite this