Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/114707
36 Visitors
38 Hits
0 Downloads
- Title
- Recognizing disfluencies in conversational speech
- Related
- IEEE transactions on audio speech and language processing, Vol. 14, Issue 5 (2006), p.1566-1573
- DOI
- 10.1109/TASL.2006.878269
- Publisher
- IEEE
- Date
- 2006
- FoR/RFCD Code(s)
-
020000 Physical Sciences
090000 Engineering
170000 Psychology And Cognitive Sciences
- Author/Creator
- Lease, Matthew
- Author/Creator
- Johnson, Mark
- Author/Creator
- Charniak, Eugene
- Description
- We present a system for modeling disfluency in conversational speech: repairs, fillers, and self-interruption points (IPs). For each sentence, candidate repair analyses are generated by a stochastic tree adjoining grammar (TAG) noisy-channel model. A probabilistic syntactic language model scores the fluency of each analysis, and a maximum-entropy model selects the most likely analysis given the language model score and other features. Fillers are detected independently via a small set of deterministic rules, and IPs are detected by combining the output of repair and filler detection modules. In the recent Rich Transcription Fall 2004 (RT-04F) blind evaluation, systems competed to detect these three forms of disfluency under two input conditions: a best-case scenario of manually transcribed words and a fully automatic case of automatic speech recognition (ASR) output. For all three tasks and on both types of input, our system was the top performer in the evaluation.
- Description
- 8 page(s)
- Subject Keyword
- 020000 Physical Sciences
- Subject Keyword
- 090000 Engineering
- Subject Keyword
- 170000 Psychology And Cognitive Sciences
- Resource Type
- journal article
- Organisation
- Macquarie University. Dept. of Computing
- Identifier
- http://hdl.handle.net/1959.14/114707
- Identifier
- ISSN:1558-7916
- Identifier
- mq-rm-2010000491
- Language
- eng
- Reviewed
