Result Details
Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech
SZŐKE, I.; SCHWARZ, P.; BURGET, L.; KARAFIÁT, M.; MATĚJKA, P.; ČERNOCKÝ, J. Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech. Lecture Notes in Computer Science, 2005, vol. 2005, no. 3658, p. 302-309. ISSN: 0302-9743.
Type
journal article
Language
English
Authors
Szőke Igor, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Schwarz Petr, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Matějka Pavel, Ing., Ph.D., DCGM (FIT), UREL (FEEC)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Schwarz Petr, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Matějka Pavel, Ing., Ph.D., DCGM (FIT), UREL (FEEC)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Abstract
This paper describes several ways of acoustic keywords spotting (KWS),based on Gaussian mixture model (GMM) hidden Markov models (HMM) andphoneme posterior probabilities from FeatureNet. Context-independentand dependent phoneme models are used in the GMM/HMM system. Thesystems were trained and evaluated on informal continuous speech. Weused different complexities of KWS recognition network and differenttypes of phoneme models. We study the impact of these parameters on theaccuracy and computational complexity, and conclude that phonemeposteriors outperform conventional GMM/HMM system.
Keywords
acoustic keyword spotting, hidden Markov model, phoneme, recognition network
URL
Published
2005
Pages
302–309
Journal
Lecture Notes in Computer Science, vol. 2005, no. 3658, ISSN 0302-9743
BibTeX
@article{BUT42913,
author="Igor {Szőke} and Petr {Schwarz} and Lukáš {Burget} and Martin {Karafiát} and Pavel {Matějka} and Jan {Černocký}",
title="Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech",
journal="Lecture Notes in Computer Science",
year="2005",
volume="2005",
number="3658",
pages="302--309",
issn="0302-9743",
url="https://www.fit.vut.cz/research/publication/7882/"
}
Projects
Augmented Multi-party Interaction, EU, Sixth Framework programme, 506811-AMI, start: 2004-01-01, end: 2006-12-31, completed
Data driven and anthropic coding and recognition of speech, GACR, Postdoktorandské granty, GP102/02/D108, start: 2002-09-01, end: 2005-08-30, completed
New trends in research and application of voice technology, GACR, Standardní projekty, GA102/05/0278, start: 2005-01-01, end: 2007-12-31, completed
Data driven and anthropic coding and recognition of speech, GACR, Postdoktorandské granty, GP102/02/D108, start: 2002-09-01, end: 2005-08-30, completed
New trends in research and application of voice technology, GACR, Standardní projekty, GA102/05/0278, start: 2005-01-01, end: 2007-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments