Using a Set of Microphones in the Automatic Speaker Recognition System of Critical Use
Keywords:
automatic speaker recognition system of critical use, pattern recognition, cepstral analysis, Gaussian mixture models, speech signalAbstract
In the article an investigation result of relationship between the quality indicators of the automated speaker recognition systems of critical use and speech material recorded on the set of microphones have been presented. The authors suggested complex decision rules on the classification of the speaker based on Gaussian mixture model parameters describing information from each microphone separately.
References
1. Биков М. М. Надійний метод виділення складових сегментів у мовному сигналі / М. М. Биков, В. В. Ковтун, Н. Г. Савінова [Електронний ресурс] // Наукові праці Вінницького національного технічного університету. — 2007. — № 1. — С. 1—6. — Режим доступу : https://praci.vntu.edu.ua/index.php/praci .
2. A short tutorial on Gaussian Mixture Models [Electronic resource] // 14th Conference on Computer and Robot Vision. Edmonton, Alberta. — May 17-19, 2017. — Access mode :
http://www.computerrobotvision.org/2010/tutorial_day/GMM_said_crv10_tutorial.pdf .
3. Reynolds D. A. Speaker verification using adapted Gaussian mixture models / D. A. Reynolds, T. F. Quatieri, R. B. Dunn // Digital Signal Processing. — 2000. — Vol. 10. — P. 19—41.
4. Kittler J. Combining classifiers / J. Kittler, M. Hatef, P.W. Duin // Proc. 7th German Workshop on Color Image Processing (ICPR'96), Erlangen, Germany, 1996. — Vol. 2. — P. 897—901.
5. NOIZEUS: Noisy speech corpus — Univ. Texas-Dallas [Electronic resource]. — Access mode :
http://ecs.utdallas.edu/loizou/speech/noizeus/ .
6. Рабинер Л. Р. Цифровая обработка речевых сигналов / Л. Р. Рабинер, Р. В. Шафер. — М. : Радио и связь, 1981. — 593 c.
7. Perceptual Linear Predictive (PLP) Analysis of Speech [Electronic resource]. — Access mode :
http://seed.ucsd.edu/mediawiki/images/5/5c/PLP.pdf .
8. RASTA Processing of Speech [Electronic resource] // LABrosa. — Access mode :
https://labrosa.ee.columbia.edu/~dpwe/papers/HermM94-rasta.pdf .
9. Reynolds D. A. Robust text-independent speaker identification using Gaussian mixture speaker models / D. A. Reynolds, R. C. Rose // IEEE Trans. Speech Audio Process. — 1995. — Vol. 3. — P. 72—83.
2. A short tutorial on Gaussian Mixture Models [Electronic resource] // 14th Conference on Computer and Robot Vision. Edmonton, Alberta. — May 17-19, 2017. — Access mode :
http://www.computerrobotvision.org/2010/tutorial_day/GMM_said_crv10_tutorial.pdf .
3. Reynolds D. A. Speaker verification using adapted Gaussian mixture models / D. A. Reynolds, T. F. Quatieri, R. B. Dunn // Digital Signal Processing. — 2000. — Vol. 10. — P. 19—41.
4. Kittler J. Combining classifiers / J. Kittler, M. Hatef, P.W. Duin // Proc. 7th German Workshop on Color Image Processing (ICPR'96), Erlangen, Germany, 1996. — Vol. 2. — P. 897—901.
5. NOIZEUS: Noisy speech corpus — Univ. Texas-Dallas [Electronic resource]. — Access mode :
http://ecs.utdallas.edu/loizou/speech/noizeus/ .
6. Рабинер Л. Р. Цифровая обработка речевых сигналов / Л. Р. Рабинер, Р. В. Шафер. — М. : Радио и связь, 1981. — 593 c.
7. Perceptual Linear Predictive (PLP) Analysis of Speech [Electronic resource]. — Access mode :
http://seed.ucsd.edu/mediawiki/images/5/5c/PLP.pdf .
8. RASTA Processing of Speech [Electronic resource] // LABrosa. — Access mode :
https://labrosa.ee.columbia.edu/~dpwe/papers/HermM94-rasta.pdf .
9. Reynolds D. A. Robust text-independent speaker identification using Gaussian mixture speaker models / D. A. Reynolds, R. C. Rose // IEEE Trans. Speech Audio Process. — 1995. — Vol. 3. — P. 72—83.
Downloads
-
PDF (Українська)
Downloads: 91
Abstract views: 195
Published
2017-06-23
How to Cite
[1]
M. M. Bykov and V. V. Kovtun, “Using a Set of Microphones in the Automatic Speaker Recognition System of Critical Use”, Вісник ВПІ, no. 3, pp. 84–91, Jun. 2017.
Issue
Section
Information technologies and computer sciences
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
