Publication Details
Spoken Term Detection System Based on a Combination of LVCSR and Phonetic Search
Fapšo Michal, Ing. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Kopecký Jiří, Ing. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
spoken term detection
The paper describes Spoken Term Detection System Based on a Combination of LVCSR and Phonetic Search.
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.