Detecting and correcting speech repairs

Authors:
Peter Heeman;James Allen
Affiliations:
University of Rochester Rochester, New York;University of Rochester Rochester, New York
Venue:
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Year:
1994

Citing 9
Cited 14

The Trains 91 Dialogues

The Trains 91 Dialogues
Dialogue Transcription Tools

Dialogue Transcription Tools
Coping with ambiguity and unknown words through probabilistic models

Computational Linguistics - Special issue on using large corpora: II
A stochastic parts program and noun phrase parser for unrestricted text

ANLC '88 Proceedings of the second conference on Applied natural language processing
Deterministic parsing of syntactic non-fluencies

ACL '83 Proceedings of the 21st annual meeting on Association for Computational Linguistics
A speech-first model for repair detection and correction

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Gemini: a natural language system for spoken-language understanding

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Integrating multiple knowledge sources for detection and correction of repairs in human-computer dialog

ACL '92 Proceedings of the 30th annual meeting on Association for Computational Linguistics
Tagging speech repairs

HLT '94 Proceedings of the workshop on Human Language Technology

Turning pervasive computing into mediated spaces

IBM Systems Journal
Empirical studies in discourse

Computational Linguistics
Effects of variable initiative on linguistic behavior in human-computer spoken natural language dialogue

Computational Linguistics
Speech repairs, intonational phrases, and discourse markers: modeling speakers' utterances in spoken dialogue

Computational Linguistics
Surface-marker-based dialog modelling: A progress report on the MAREDI project

Natural Language Engineering
Applying repair processing in Chinese homophone disambiguation

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Intonational boundaries, speech repairs and discourse markers: modeling spoken dialog

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Characterizing and recognizing spoken corrections in human-computer dialogue

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Learning to identify fragmented words in spoken discourse

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
Tagging speech repairs

HLT '94 Proceedings of the workshop on Human Language Technology
A Tagged Corpus-Based Study for Repeats and Self-repairs Detection in French Transcribed Speech

TSD '08 Proceedings of the 11th international conference on Text, Speech and Dialogue
SCREEN: learning a flat syntactic and semantic spoken language analysis using artificial neural networks

Journal of Artificial Intelligence Research
Exploring features for identifying edited regions in disfluent sentences

Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
Orthographic transcription for spoken tunisian arabic

CICLing'13 Proceedings of the 14th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the repair pattern. The repair pattern is built by finding word matches and word replacements, and identifying fragments and editing terms. Rather than using a set of prebuilt templates, we build the pattern on the fly. In a the fair test, our method, when combined with a statistical model to filter possible repairs, was successful at detecting and correcting 80% of the repairs, without using prosodic information or a parser.