Přejít na obsah

Detail publikace

Citace

Radová, V. and Psutka, J. : An Approach to Speaker Identification Using Multiple Classifiers . 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'97), vol. Volume II: Speech Processing, p. 1135-1138, Institute of Electrical and Electronics Engineers, Inc., Munich, Germany, 1997.

Abstrakt

Presented paper takes interest in a speaker identification problem. The attributes representing voice of a particular speaker are obtained from very short segments of the speech waveform corresponding only to one pitch period of vowels. The patterns formed from the samples of a pitch period waveform are either matched in time domain by use of a nonlinear time warping method, known as dynamic time warping (DTW), or they are converted into the cepstral coefficients and compared using the cepstral distance measure. Since an uttered speech signal usually contains a lot of vowels the techniques using a combination both various classifiers and multiple classifier outputs are considered in the decision making process. Experiments performed for hundred speakers are described at the end of this paper.

Detail publikace

Název: An Approach to Speaker Identification Using Multiple Classifiers
Autor: Radová, V. ; Psutka, J.
Název - česky: Přístup k identifikaci řečníka s využitím více klasifikátorů
Jazyk publikace: anglicky
Datum vydání: 21.4.1997
Rok vydání: 1997
Typ publikace: Stať ve sborníku
Název časopisu / knihy: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'97)
Číslo vydání: Volume II: Speech Processing
Strana: 1135 - 1138
DOI: 10.1109/ICASSP.1997.596142
ISBN: 0-8186-7919-0
Nakladatel: Institute of Electrical and Electronics Engineers, Inc.
Místo vydání: Munich, Germany
Datum: 21.4.1997 - 24.4.1997
/ 2012-11-14 16:40:21 /

Klíčová slova

speaker identification, combination of classfiers

BibTeX

@INPROCEEDINGS{RadovaV_1997_AnApproachto,
 author = {Radov\'{a}, V. and Psutka, J.},
 title = {An Approach to Speaker Identification Using Multiple Classifiers},
 year = {1997},
 publisher = {Institute of Electrical and Electronics Engineers, Inc.},
 journal = {1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'97)},
 address = {Munich, Germany},
 volume = {Volume II: Speech Processing},
 pages = {1135-1138},
 ISBN = {0-8186-7919-0},
 doi = {10.1109/ICASSP.1997.596142},
 url = {http://www.kky.zcu.cz/en/publications/RadovaV_1997_AnApproachto},
}