A speech-first model for repair detection and correction

Authors:
Christine Nakatani;Julia Hirschberg
Affiliations:
Harvard University, Cambridge, MA;2D-450, AT&T Bell Laboratories, Murray Hill, NJ
Venue:
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Year:
1993

Citing 4
Cited 15

A computational grammar of discourse-neutral prosodic phrasing in English

Computational Linguistics
Deterministic parsing of syntactic non-fluencies

ACL '83 Proceedings of the 21st 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
Automatic detection and correction of repairs in human-computer dialog

HLT '91 Proceedings of the workshop on Speech and Natural Language

Interface techniques for minimizing disfluent input to spoken language systems

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Gesture Patterns during Speech Repairs

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Empirical studies in discourse

Computational Linguistics
Applying repair processing in Chinese homophone disambiguation

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
A model for robust processing of spontaneous speech by integrating viable fragments

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Detecting and correcting speech repairs

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
A grammar and a parser for spontaneous speech

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
A parser coping with self-repaired Japanese utterances and large corpus-based evaluation

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Processing self corrections in a speech to speech system

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Processing Japanese self-correction in speech dialog systems

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Tagging speech repairs

HLT '94 Proceedings of the workshop on Human Language Technology
SCREEN: learning a flat syntactic and semantic spoken language analysis using artificial neural networks

Journal of Artificial Intelligence Research
Contextual maximum entropy model for edit disfluency detection of spontaneous speech

ISCSLP'06 Proceedings of the 5th international conference on Chinese Spoken Language Processing
Acoustic transformations to improve the intelligibility of dysarthric speech

SLPAT '11 Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies
A monotonic statistical machine translation approach to speaking style transformation

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

Interpreting fully natural speech is an important goal for spoken language understanding systems. However, while corpus studies have shown that about 10% of spontaneous utterances contain self-corrections, or REPAIRS, little is known about the extent to which cues in the speech signal may facilitate repair processing. We identify several cues based on acoustic and prosodic analysis of repairs in a corpus of spontaneous speech, and propose methods for exploiting these cues to detect and correct repairs. We test our acoustic-prosodic cues with other lexical cues to repair identification and find that precision rates of 89--93% and recall of 78--83% can be achieved, depending upon the cues employed, from a prosodically labeled corpus.