Paper Info
Title
Anchor point detection for continuous speech recognition in Spanish: the spotting of phonetic events
Abstract
Several techniques have been used to constrain the search space in an HMM based continuous speech recognition system (grammar, beam search, etc.) in order to reduce computation without significant lose in performance (H. Ney, 1993). The use of anchor points is a state-of-the-art technique that has already been used in some systems (D. Lubensky, 1987; H. Murveit et al., 1993; M. Adda-Decker, 1989). This approach has lead us to a bottom-up strategy in a continuous speech recognition system in which the first module performs the spotting of predefined phonetic events and the second module uses them as anchor points in order to guide the HMM based recognition task. The paper describes the definition of phonetic events for Spanish (based on expert knowledge of language) and the algorithms used for their detection and classification. Performance figures are presented
Year
DOI
Venue
1996
10.1109/ICSLP.1996.607276
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference
Keywords
Field
DocType
hidden Markov models,natural languages,search problems,speech processing,speech recognition,HMM based continuous speech recognition system,HMM based recognition task,Spanish,anchor point detection,bottom-up strategy,continuous speech recognition,predefined phonetic event spotting,search space,state-of-the-art technique
Speech processing,Speech analytics,Voice activity detection,Computer science,Beam search,Speech recognition,Natural language,Speaker recognition,Natural language processing,Artificial intelligence,Hidden Markov model,Spotting
Conference
Volume
ISBN
Citations 
4
0-7803-3555-4
0
PageRank 
References 
Authors
0.34
6
2
Name
Order
Citations
PageRank
Manuel A. Leandro162.35
José Manuel Pardo215230.36