Publication Details

Recognition of Speech with Non-random Attributes

BURGET Lukáš and ČERNOCKÝ Jan. Recognition of Speech with Non-random Attributes. In: 6th International Conference, TSD 2003 České Budějovice, Czech Republic, September 2003 Proceedings. České Budějovice: Springer Verlag, 2003, p. 6. ISBN 3-540-20024-X. ISSN 0302-9743.
Czech title
Rozpoznavání řeči s nenáhodnými atributy
Type
conference paper
Language
english
Authors
URL
Keywords

Speech recognition, Hidden Markov Models, HMM

Abstract

Recognition of Speech, where utterances are supposed to have assigned attributes with Non-random character

Annotation

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.

Published
2003
Pages
6
Journal
Lecture Notes in Computer Science, vol. 2003, no. 9, ISSN 0302-9743
Proceedings
6th International Conference, TSD 2003 České Budějovice, Czech Republic, September 2003 Proceedings
Conference
International Conference on Text Speech and Dialogue, TSD 2003, Ceske Budejovice, CZ
ISBN
3-540-20024-X
Publisher
Springer Verlag
Place
České Budějovice, CZ
BibTeX
@INPROCEEDINGS{FITPUB7780,
   author = "Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Recognition of Speech with Non-random Attributes",
   pages = 6,
   booktitle = "6th International Conference, TSD 2003 \v{C}esk\'{e} Bud\v{e}jovice, Czech Republic, September 2003 Proceedings",
   journal = "Lecture Notes in Computer Science",
   volume = 2003,
   number = 09,
   year = 2003,
   location = "\v{C}esk\'{e} Bud\v{e}jovice, CZ",
   publisher = "Springer Verlag",
   ISBN = "3-540-20024-X",
   ISSN = "0302-9743",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7780"
}
Back to top