Nonnative speech recognition based on bilingual model modification

Qingqing Zhang, Jielin Pan, Shui Duen Chan, Yonghong Yan

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review


This paper presents a novel bilingual model modification approach to improve nonnative speech recognition accuracy when the variations of accented pronunciations occur. Each state of baseline nonnative acoustic model is modified with several candidate states from the auxiliary acoustic model, which is trained on speakers' mother language. State mapping criterion and n-best candidates are investigated, and different numbers of Gaussian mixtures of the auxiliary acoustic model are compared based on a grammar-constrained speech recognition system. Using this bilingual model modification approach, compared to the nonnative acoustic model which has already been well trained by adaptation technique MAP, the Phrase Error Rate further achieves a 5.83% relative reduction, while only a small relative increase on Real Time Factor occurs.
Original languageEnglish
Title of host publication2009 IEEE International Conference on Fuzzy Systems - Proceedings
Number of pages5
Publication statusPublished - 10 Dec 2009
Event2009 IEEE International Conference on Fuzzy Systems - Jeju Island, Korea, Republic of
Duration: 20 Aug 200924 Aug 2009


Conference2009 IEEE International Conference on Fuzzy Systems
Country/TerritoryKorea, Republic of
CityJeju Island

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Nonnative speech recognition based on bilingual model modification'. Together they form a unique fingerprint.

Cite this