Dynamic multiple pronunciation incorporation in a refined search space for reading miscue detection

  • Changliang Liu
  • , Fuping Pan
  • , Fengpei Ge
  • , Bin Dong
  • , Shuiduen Chen
  • , Yonghong Yan

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

Abstract

Error prediction is important for detecting reading miscues by a reading tutor. In order to incorporate the error prediction into the decoder of a conventional speech recognizer, this paper proposes an algorithm of Dynamic Multiple Pronunciation Incorporation (DMPI). It solves the confliction between the coverage of errors and the perplexity increase of search space. A multiple pronunciation model (MPM) is developed to model the misreading errors. The pronunciation variants referred to in current reference are extracted from MPM and added to the search space of the recognizer – a refined state network before recognizing. The original state network is redeveloped to reserve some redundant fan-in and fan-out nodes which make the merging of the original state network and the additional state network very easy. The experiment result proved effectiveness of this algorithm. The EER is decreased by about 9.5%.

Original languageEnglish
Title of host publicationThe Sixth International Symposium on Neural Networks (ISNN 2009)
EditorsHongwei Wang, Yi Shen, Zhigang Zeng, Tingwen Huang
PublisherSpringer Verlag
Pages379-389
Number of pages11
ISBN (Electronic)9783642012167
ISBN (Print)9783642012150
DOIs
Publication statusPublished - 3 May 2009
Event6th International Symposium of Neural Networks, ISNN 2009 - Wuhan, China
Duration: 26 May 200929 May 2009

Publication series

NameAdvances in Intelligent and Soft Computing
Volume56
ISSN (Print)1867-5662
ISSN (Electronic)1860-0794

Conference

Conference6th International Symposium of Neural Networks, ISNN 2009
Country/TerritoryChina
CityWuhan
Period26/05/0929/05/09

Keywords

  • CALL
  • Decoder
  • Multiple pronunciation model
  • Reading tutor
  • State network

ASJC Scopus subject areas

  • General Computer Science

Fingerprint

Dive into the research topics of 'Dynamic multiple pronunciation incorporation in a refined search space for reading miscue detection'. Together they form a unique fingerprint.

Cite this