DocumentCode
2981059
Title
On cross-language experiments and data-driven units for ALISP (Automatic Language Independent Speech Processing)
Author
Constantinescu, A. ; Chollet, G.
Author_Institution
ENST, Paris, France
fYear
1997
fDate
14-17 Dec 1997
Firstpage
606
Lastpage
613
Abstract
The authors discuss the cross-language use of phonemic models, in the context of their research goal: Automatic Language Independent Speech Processing (ALISP). A method is proposed and demonstrated for creating adequate representations of target vocabulary words through sub word models, given minimal training data. Also, the topic of data-driven determination of language-independent acoustic segments for speech recognition is addressed
Keywords
natural language interfaces; speech processing; speech recognition; vocabulary; ALISP; automatic language independent speech processing; cross-language experiments; data-driven units; language-independent acoustic segments; minimal training data; phonemic models; speech recognition; subword models; vocabulary words; Context modeling; Hidden Markov models; Humans; Loudspeakers; Natural languages; Spatial databases; Speech processing; Speech recognition; Training data; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on
Conference_Location
Santa Barbara, CA
Print_ISBN
0-7803-3698-4
Type
conf
DOI
10.1109/ASRU.1997.659142
Filename
659142
Link To Document