Přejít na obsah

Publikace

Detail publikace

Citace

Šmídl, L. and Müller, L. and Psutka, J. : Improving a keyword spotting system using phoneme sequence . WSEAS TRANSACTIONS on COMPUTER, p. 751-755, WSEAS, Greece, 2003.

Abstrakt

This paper presents a technique for improving keyword spotting. The main idea is based on the combination of a standard keyword spotting system working with a filler model with a phone recognizer. If the filler model is well designed it produces a phoneme sequence corresponding to the investigated utterance. This phoneme sequence generated by a filler model can be used to reject incorrectly detected keywords. The quality of this technique depends on how good is the acoustic match between an incoming utterance and a bigram phoneme filler model.

Detail publikace

Název: Improving a keyword spotting system using phoneme sequence
Autor: Šmídl, L. ; Müller, L. ; Psutka, J.
Jazyk publikace: anglicky
Datum vydání: 13.10.2003
Rok vydání: 2003
Typ publikace: Stať ve sborníku
Název časopisu / knihy: WSEAS TRANSACTIONS on COMPUTER
Strana: 751 - 755
Nakladatel: WSEAS
Místo vydání: Greece
Datum: 13.10.2003 - 15.10.2003
/ /

Klíčová slova

keyword spotting, filler model, confidence measure, acoustic baseforms

Klíčová slova v češtině

detekce klíčových slov, model neklíčové části, rozpoznávání řeči, míra důvěry

BibTeX

@INPROCEEDINGS{SmidlL_2003_Improvingakeyword,
 author = {\v{S}m\'{i}dl, L. and M\"{u}ller, L. and Psutka, J.},
 title = {Improving a keyword spotting system using phoneme sequence},
 year = {2003},
 publisher = {WSEAS},
 journal = {WSEAS TRANSACTIONS on COMPUTER},
 address = {Greece},
 pages = {751-755},
 url = {http://www.kky.zcu.cz/en/publications/SmidlL_2003_Improvingakeyword},
}