Doc. Dr. Ing. Jan Černocký

Szőke, I., Fapšo, M., Karafiát, M., Burget, L., Grézl, F., Schwarz, P., Glembek, O., Matějka, P., Kopecký, J., Černocký, J.: Spoken Term Detection System Based on a Combination of LVCSR and Phonetic Search, Brno, CZ, 2007, p. 1-1
Publication language:english
Original title:Spoken Term Detection System Based on a Combination of LVCSR and Phonetic Search
Title (cs):Detekce dotazů v mluvených dokumentech založená na kombinaci LVCSR a fonetického vyhledávání
Pages:1-1
Conference:Machine Learning and Multimodal Interaction
Place:Brno, CZ
Year:2007
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2007/szoke_kws_ins_mlmi_poster_2007.pdf [PDF]
Keywords
spoken term detection
Annotation
The paper describes Spoken Term Detection System Based on a Combination of LVCSR and Phonetic Search.
Abstract
The paper presents Brno University of Technology (BUT) system for indexing and search of speech, combining LVCSR and phonetic approach. It brings a complete description of individual building blocks of the system from signal processing, through the recognizers, indexing and search until the normalization of detection scores. It also describes the data used in the first edition of NIST Spoken term detection (STD) evaluation. The results are presented on three US-English conditions - meetings, broadcast news and conversational telephone speech, in terms of detection error trade-off (DET) curves and term-weighted values (TWV) metrics defined by NIST.

Your IPv4 address: 54.226.5.29
Switch to IPv6 connection

DNSSEC [dnssec]