Continuous speech recognition with automatically selected acoustic prototypes obtained by either bootstrapping or clustering

Autor:	Lalit R. Bahl, A. Cole, A. Nadas, Paul S. Cohen, Raimo Bakis, Burn L. Lewis, Robert Leroy Mercer, Frederick Jelinek
Rok vydání:	2005
Předmět:	Audio mining Vocabulary Voice activity detection Computer science media_common.quotation_subject Speech recognition Acoustic model Bootstrapping (linguistics) Speech corpus Speech processing VoxForge Speech analytics Cluster analysis Natural language media_common
Zdroj:	ICASSP
DOI:	10.1109/icassp.1981.1171177
Popis:	Automatic selection of acoustic prototypes is an important step towards making speech recognition systems automatically adaptable to new speakers. Two methods for automatically obtaining a set of acoustic prototypes for use by a centisecond labeling acoustic processor are described. One method is based on bootstrapping, the other on clustering. Recognition results using these automatically obtained prototypes on the 1000-word vocabulary natural language Laser Patent task are presented. These results are compared to those from an experiment in which the acoustic prototypes were manually selected.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fe19a815398b92a93da4a98069165ae2 https://doi.org/10.1109/icassp.1981.1171177 Zobrazit plný text záznamu