Publication detail

Recognition of Speech with Non-random Attributes

BURGET, L., ČERNOCKÝ, J.

Original Title

Recognition of Speech with Non-random Attributes

Type

conference paper

Language

English

Original Abstract

Most of current speech recognition systems are based on Hidden Markov Models assuming that speech features are sequence of stationary stochastic processes. However, there are certain speech attributes, such as background noise type or speaker voice color, that do not have stochastic character. This fact is often ignored, by designers of robust speaker independent recognition system. In this work, we investigate how the performance of a noisy speech recognition can be improved provided that we have prior knowledge about type and level of noise. Next, recognizer that is using separate models, each trained on a particular type and level of noise, is proposed for more appropriate modeling of speech.

Keywords

Speech recognition, Hidden Markov Models, HMM

Authors

BURGET, L., ČERNOCKÝ, J.

Released

17. 6. 2003

Publisher

Springer Verlag

Location

České Budějovice

ISBN

3-540-20024-X

Book

6th International Conference, TSD 2003 České Budějovice, Czech Republic, September 2003 Proceedings

ISBN

0302-9743

Periodical

Lecture Notes in Computer Science

Year of study

2003

Number

09

State

Federal Republic of Germany

Pages from

1

Pages to

6

Pages count

6

URL

BibTex

@inproceedings{BUT21496,
  author="Lukáš {Burget} and Jan {Černocký}",
  title="Recognition of Speech with Non-random Attributes",
  booktitle="6th International Conference, TSD 2003 České Budějovice, Czech Republic, September 2003 Proceedings",
  year="2003",
  journal="Lecture Notes in Computer Science",
  volume="2003",
  number="09",
  pages="6",
  publisher="Springer Verlag",
  address="České Budějovice",
  isbn="3-540-20024-X",
  issn="0302-9743",
  url="http://www.kiv.zcu.cz/events/tsd2003/, http://www.fit.vutbr.cz/~burget/phd_activities/burget_tsd03.pdf"
}