Work

A TAG-based noisy channel model of speech repairs

Year: 2004

Type: conference-paper

Abstract: This paper describes a noisy channel model of speech repairs, which can identify and correct repairs in speech transcripts. A syntactic parser is used as the source model, and a novel type of TAG-based transducer is the channel model. The use of TAG is motivated by the intuition that the reparandum is a "rough copy" of the repair. The model is trained and tested on the Switchboard disfluency-annotated corpus.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.3115/1218955.1218960

Authors: Mark Johnson, Eugene Charniak

Institution: Brown University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W2169058332

FWCI: 4.968

Cites: 8

Cited by: 129

Related to: 10