Title :
Speaker intention modeling for large vocabulary Mandarin spoken dialogues
Author :
Yang, Yen-Ju ; Chien, Lee-Feng ; Lee, Lin-shan
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Abstract :
The paper presents a statistical speaker intention modeling approach of speech act types (SAT´s) (M. Nagata and T. Morimoto, 1993) prediction for large vocabulary Mandarin spoken dialogues. A SAT is an abstraction of speaker´s intention in terms of the type of action that the speaker intends by the utterance. With this approach, spoken dialogue systems can be constructed to predict speaker´s intention and make a proper action in advance
Keywords :
interactive systems; natural language interfaces; natural languages; speech processing; statistical analysis; SAT; large vocabulary Mandarin spoken dialogues; speech act types; spoken dialogue systems; statistical speaker intention modeling approach; utterance; Computer science; Data mining; Databases; Information science; Mutual information; Predictive models; Redundancy; Speech; Telephony; Vocabulary;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607461
