Automatic Spelling Correction for ASR Corpus in Traditional Chinese Language using Seq2Seq Models

Yu Chieh Chao, Chia Hui Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The goal of Automatic Speech Recognition (ASR) service is to translate spoken language into text. There exist many factors that will degrade the performance of the ASR system, such as environmental noise, human pronunciation, etc. This research focuses on automatic spelling correction for traditional Chinese corpus generated by ASR systems. We show that a Sequence to Sequence (Seq2Seq) neural network model with attention mechanism could be improved by adding pointer network with auxiliary phoneme features of the input word sequence.

Original languageEnglish
Title of host publicationProceedings - 2020 International Computer Symposium, ICS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages553-558
Number of pages6
ISBN (Electronic)9781728192550
DOIs
StatePublished - Dec 2020
Event2020 International Computer Symposium, ICS 2020 - Tainan, Taiwan
Duration: 17 Dec 202019 Dec 2020

Publication series

NameProceedings - 2020 International Computer Symposium, ICS 2020

Conference

Conference2020 International Computer Symposium, ICS 2020
Country/TerritoryTaiwan
CityTainan
Period17/12/2019/12/20

Keywords

  • automatic speech recognition
  • pointer network
  • sequence to sequence model
  • spelling check

Fingerprint

Dive into the research topics of 'Automatic Spelling Correction for ASR Corpus in Traditional Chinese Language using Seq2Seq Models'. Together they form a unique fingerprint.

Cite this