论文信息 - Combining the detection and correction of speech repairs

Combining the detection and correction of speech repairs

Previous approaches to detecting and correcting speech repairs have for the most part separated these two problems. We present a statistical model of speech repairs that uses information about the possible correction to help decide whether a speech repair actually occurred. By better modeling the interactions between detection and correction, we are able to improve our detection results.

James F. Allen | Peter A. Heeman | Kyung-ho Loken-Kim

[1] Chung Hee Hwang,et al. The TRAINS project: a case study in building a conversational planning agent , 1994, J. Exp. Theor. Artif. Intell..

[2] W. Levelt,et al. Monitoring and self-repair in speech , 1983, Cognition.

[3] James F. Allen,et al. Deyecting and Correcting Speech Repairs , 1994, ACL.

[4] Robin J. Lickley,et al. Processing disfluent speech: recognising disfluency before lexical access , 1992, ICSLP.

[5] Kenneth Ward Church. A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text , 1988, ANLP.

[6] Tsuyoshi Morimoto,et al. Similarity-based identification of repairs in Japanese spoken language , 1994, ICSLP.

[7] John Bear,et al. Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-Computer Dialog , 1992, ACL.

[8] Donald Hindle,et al. Deterministic Parsing of Syntactic Non-fluencies , 1983, ACL.

[9] Leo Breiman,et al. Classification and Regression Trees , 1984 .