Speech act modeling in a spoken dialog system using a fuzzy fragment-class Markov model

Speech Communication

Volumn 38, Issue 1-2, 2002, Pages 183-199

  Wu, Chung Hsien ^a   Yan, Gwo Lang ^a   Lin, Chien Liang ^a  

^a NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

Author keywords

Fuzzy fragment class Markov model; Speech act; Spoken language; Verification

Indexed keywords

SPEECH ACT (SA);

DATABASE SYSTEMS; FUZZY SETS; MARKOV PROCESSES; PROBABILITY; SPEECH ANALYSIS;

SPEECH COMMUNICATION;

EID: 0036722771     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00052-8     Document Type: Article

References (22)

1. Grammar Fragment acquisition using syntactic and semantic clustering
2. Dialog in the RAILTEL telephone-based system
3. The design of a mandarin chinese spoken dialog system
4. Fuzzy trigram model for speech act analysis of utterances in dialogs
5. Classifying words for improved statistical language models
6. Unknown word and phrase extraction using a phrase-like-unit-based likelihood ratio
7. A multi-keyword spotter for the application of the TL phone directory assistant service
8. Algorithms for bigram and trigram word clustering
9. WHEELS: A conversational system in the automobile classification domain
10. A speech understanding system based on statistical representation of semantics
11. Stochastic language adaptation over time and state in natural spoken dialog systems
12. Structuring utterance records of requirements elicitation meetings based on speech act theory. Requirements engineering
13. Toward an automated directory information system
14. Fuzzy gaussian mixture models for speaker recognition
15. A proposed decision rule for speaker recognition based on fuzzy C-means clustering
16. A conversational agent for food ordering dialog based on venus dictate
17. Automatic acquisition of salient grammar fragments for call-type classification
18. Template-driven generation of prosodic information for Chinese concatenative synthesis
19. Spoken dialogue system using corpus-based hidden Markov model