Publication detail

Phoneme based acoustics keyword spotting in informal continuous speech

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

Original Title

Phoneme based acoustics keyword spotting in informal continuous speech

Type

conference paper

Language

English

Original Abstract

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

Keywords

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

Authors

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

RIV year

2005

Released

16. 5. 2005

Publisher

Faculty of Electrical Engineering and Communication BUT

Location

Brno

ISBN

80-214-2904-6

Book

Radioelektronika 2005

Pages from

195

Pages to

198

Pages count

4

URL

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"
}