AN AUDITORY-BASED SPEAKER IDENTIFICATION SYSTEM IN ACOUSTIC NOISES
Abstract
The speaker recognition system in acoustic noises with the use of anthropomorphic speech signal processing is considered. A transform based on the cochlear model and its applications for speaker recognition are described in details. The characteristic vector obtained on the basis of this transform used as features for speaker identification. Neural network of direct distribution as decision rules are used. The results of the developed recognition systems of speaker identification are given.
About the Authors
D. N. Kruchok
Белорусский государственный университет информатики и радиоэлектроники
Belarus
Belarus
A. A. Petrovsky
Белорусский государственный университет информатики и радиоэлектроники
Belarus
Belarus
References
1. Сорокин В.Н., Вьюгин В.В., Тананыкин А.А. // Информационные процессы. 2012. Т. 12, № 1. С. 1-30.
2. Информационное агентство. Бизнес. Новости компаний [Электронный ресурс].- Режим доступа: http://www.interfax.by/news/belarus/1196246. - Дата доступа : 17.12.2015.
3. Togneri R., Pullella D. // IEEE Circuits and systems magazine. 2011. P. 23-58.
4. Mammone R., Zhang X., Ramachandran R. // IEEE Signal processing magazine 1996. Vol. 13, № 5. P. 58-71.
5. Furui S. // IEEE Trans. Acoustics Speech Signal Process. 1981. Vol. 29, № 2. P. 254-272.
6. Hermansky H., Morgan N. // IEEE Trans. Speech Audio Process. 1994. Vol. 2, № 4. P. 578-589.
7. Qi Li // Proc. IEEE Workshop Applicat. Signal Process. Audio Acoust. New York, 2009. P. 181-184.
8. Qi Li // IEEE Transactions Audio, Speech, and Language Processing. 2011. Vol. 19, № 6. P. 1791-1801.
9. Petrovsky A.A., Likhachov D.S., Wan W. // Computing. 2004. Vol. 3, № 1. P. 75-83.
10. The PASCAL CHiME speech separation and recognition challenge [Electronic resource]. - Mode of access: http://spandh.dcs.shef.ac.uk/projects/chime/PCC/results.html. - Date of access : 19.01.2016.
Review
For citations:
Kruchok D.N., Petrovsky A.A. AN AUDITORY-BASED SPEAKER IDENTIFICATION SYSTEM IN ACOUSTIC NOISES. Doklady BGUIR. 2016;(4):47-53. (In Russ.)
Views: 342
Email this article 