Using speech recognition technique for constructing a phonetically transcribed Taiwanese (Min-nan) text corpus

Min Siong Liang*, Ren Yuan Lyu, Yuang Chin Chiang

*Corresponding author for this work

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

3 Scopus citations

Abstract

Collection of Taiwanese text corpus with phonetic transcription suffers from the problems of multiple pronunciation variation. By augmenting the text with speech, and using automatic speech recognition with a sausage searching net constructed from the multiple pronunciations of the text corresponding to its speech utterance, we are able to reduce the effort for phonetic transcription. By using the multiple pronunciation lexicon, the error rate of transcription 13.94% was achieved. Further improvement can be achieved by adapting the pronunciation lexicon with pronunciation variation (PV) rules derived from a manual corrected speech corpus. The PV rules can be categorized into two kinds: the knowledge-based and data-driven rules. By incorporating the PV rules, the error rate reduction 13.63% could be achieved. Although the technique was developed for Taiwanese speech, it could also be adapted easily to be applied in the other similar "minority" Chinese spoken languages.

Original languageEnglish
Title of host publicationINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
PublisherInternational Speech Communication Association
Pages193-196
Number of pages4
ISBN (Print)9781604234497
StatePublished - 2006
EventINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA, United States
Duration: 17 09 200621 09 2006

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume1
ISSN (Electronic)1990-9772

Conference

ConferenceINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
Country/TerritoryUnited States
CityPittsburgh, PA
Period17/09/0621/09/06

Keywords

  • Multiple pronunciations
  • Phonetic transcription
  • Pronunciation variation
  • Taiwanese
  • Text corpus

Fingerprint

Dive into the research topics of 'Using speech recognition technique for constructing a phonetically transcribed Taiwanese (Min-nan) text corpus'. Together they form a unique fingerprint.

Cite this