Publication detail

Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech

SZŐKE, I., SCHWARZ, P., BURGET, L., KARAFIÁT, M., MATĚJKA, P., ČERNOCKÝ, J.

Original Title

Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech

Type

journal article - other

Language

English

Original Abstract

This paper describes several ways of acoustic keywords spotting (KWS), based on Gaussian mixture model (GMM) hidden Markov models (HMM) and phoneme posterior probabilities from FeatureNet. Context-independent and dependent phoneme models are used in the GMM/HMM system. The systems were trained and evaluated on informal continuous speech. We used different complexities of KWS recognition network and different types of phoneme models. We study the impact of these parameters on the accuracy and computational complexity, and conclude that phoneme posteriors outperform conventional GMM/HMM system.

Keywords

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

Authors

SZŐKE, I., SCHWARZ, P., BURGET, L., KARAFIÁT, M., MATĚJKA, P., ČERNOCKÝ, J.

RIV year

2005

Released

31. 8. 2005

ISBN

0302-9743

Periodical

Lecture Notes in Computer Science

Year of study

2005

Number

3658

State

Federal Republic of Germany

Pages from

302

Pages to

309

Pages count

8

URL

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="8",
  issn="0302-9743",
  url="https://www.fit.vutbr.cz/~szoke/papers/tsd_2005.pdf, https://www.fit.vutbr.cz/~szoke/papers/keywordspotting_poster_2005.pdf"
}