Disfluency correction of spontaneous speech using conditional random fields with variable-length features

Jui Feng Yeh, Chung Hsien Wu, Wei Yen Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper presents an approach to detecting and correcting edit disfluency based on conditional random fields with variable-length features. The variable-length features consist of word, chunk and sentence features. Conditional random fields (CRF) are adopted to model the properties of the edit disfluency, including repair, repetition and restart, for edit disfluency detection. For the evaluation of the proposed method, Mandarin conversational dialogue corpus (MCDC) is used. The detection error rate of edit word is 17.3%. Compared with DF-gram, Maximum Entropy and the approach combining language model and alignment model, the proposed approach achieves 11.7%, 8% and 3.9% improvements, respectively. The experimental results show that the proposed model outperforms other methods and efficiently detects and corrects edit disfluency in spontaneous speech.

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages549-552
Number of pages4
Publication statusPublished - 2007 Dec 1
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: 2007 Aug 272007 Aug 31

Publication series

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

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CountryBelgium
CityAntwerp
Period07-08-2707-08-31

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Software
  • Modelling and Simulation
  • Linguistics and Language
  • Communication

Fingerprint Dive into the research topics of 'Disfluency correction of spontaneous speech using conditional random fields with variable-length features'. Together they form a unique fingerprint.

Cite this