Result Details

Phoneme based acoustics keyword spotting in informal continuous speech

SZŐKE, I.; SCHWARZ, P.; BURGET, L.; KARAFIÁT, M.; ČERNOCKÝ, J. Phoneme based acoustics keyword spotting in informal continuous speech. Radioelektronika 2005. Brno: Faculty of Electrical Engineering and Communication BUT, 2005. p. 195-198. ISBN: 80-214-2904-6.
Type
conference paper
Language
English
Authors
Abstract

This paper describes several ways of keywords spotting (KWS), based onGaussian mixture (GM) hidden Markov modelling (HMM).Context-independent and dependent phoneme models are used in oursystem. The system was trained and evaluated on informal continuousspeech. We used different complexities of KWS recognition networks anddifferent types of phoneme models. The impact of these parameters onthe accuracy and computational complexity is investigated.

Keywords

acoustic keyword spotting, hidden Markov model, phoneme, recognition network

URL
Published
2005
Pages
195–198
Proceedings
Radioelektronika 2005
Conference
15th International Czech-Slovak Scientific conference Radioelektronika 2005
ISBN
80-214-2904-6
Publisher
Faculty of Electrical Engineering and Communication BUT
Place
Brno
BibTeX
@inproceedings{BUT21490,
  author="Igor {Szőke} and Petr {Schwarz} and Lukáš {Burget} and Martin {Karafiát} and Jan {Černocký}",
  title="Phoneme based acoustics keyword spotting in informal continuous speech",
  booktitle="Radioelektronika 2005",
  year="2005",
  pages="195--198",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  address="Brno",
  isbn="80-214-2904-6",
  url="https://www.fit.vutbr.cz/~szoke/papers/radioelektronika_2005.pdf"
}
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
Research groups
Departments
Back to top