hrcak mascot   Srce   HID

Izvorni znanstveni članak

PC-Based System for Robust Speaker Recognition

Stefan Hadjitodorov ; Central Laboratory of Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria
Boyan Boyanov ; Central Laboratory of Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria

Puni tekst: engleski, pdf (5 MB) str. 415-423 preuzimanja: 74* citiraj
APA 6th Edition
Hadjitodorov, S. i Boyanov, B. (1998). PC-Based System for Robust Speaker Recognition. Journal of computing and information technology, 6 (4), 415-423. Preuzeto s https://hrcak.srce.hr/150207
MLA 8th Edition
Hadjitodorov, Stefan i Boyan Boyanov. "PC-Based System for Robust Speaker Recognition." Journal of computing and information technology, vol. 6, br. 4, 1998, str. 415-423. https://hrcak.srce.hr/150207. Citirano 28.02.2021.
Chicago 17th Edition
Hadjitodorov, Stefan i Boyan Boyanov. "PC-Based System for Robust Speaker Recognition." Journal of computing and information technology 6, br. 4 (1998): 415-423. https://hrcak.srce.hr/150207
Harvard
Hadjitodorov, S., i Boyanov, B. (1998). 'PC-Based System for Robust Speaker Recognition', Journal of computing and information technology, 6(4), str. 415-423. Preuzeto s: https://hrcak.srce.hr/150207 (Datum pristupa: 28.02.2021.)
Vancouver
Hadjitodorov S, Boyanov B. PC-Based System for Robust Speaker Recognition. Journal of computing and information technology [Internet]. 1998 [pristupljeno 28.02.2021.];6(4):415-423. Dostupno na: https://hrcak.srce.hr/150207
IEEE
S. Hadjitodorov i B. Boyanov, "PC-Based System for Robust Speaker Recognition", Journal of computing and information technology, vol.6, br. 4, str. 415-423, 1998. [Online]. Dostupno na: https://hrcak.srce.hr/150207. [Citirano: 28.02.2021.]

Sažetak
A PC-based system for robust speaker recognition is proposed. It includes three one level recognition methods and a two level classifier. New procedures for voice analysis are proposed: a) Robust periodicity/ aperiodicity separation by neural networks; b) Robust pitch period detection; c) Analysis of the temporal, spectral and cepstral speech characteristics. Several pattern recognition methods are implemented, because they allow analysis of different static and dynamic characteristics of the speech parameters:

1) Prototype distribution maps (PDM). The PDM is used because: a) weight vectors of PDM's neurons try to imitate the probability density function - pdf (whatever complex the form of the pdf is) and less significant PDM's neurons are eliminated by filtering.

2) AR-vector models (ARVM). The ARVM are used because they model the evolution of speech parameters.

3) The covariance approach combined with the arithmetic-harmonic sphericity measure, because this method performs effective speaker recognition over noisy signals.

4) Two level classifier, incorporating the discriminant capabilities and classification power of the multilayer perceptron (MLP) with the pdf's estimating, statistical modeling and compressing power of the PDM. The first level consists of several PDMs and the second - of MLP networks.

The experiments show that the proposed system is an efficient and useful tool for speaker recognition over clean and noisy signals.

Ključne riječi
Speaker identification; Neural networks; Self-organizing map; MLP network; Two-level classifier

Hrčak ID: 150207

URI
https://hrcak.srce.hr/150207

Posjeta: 132 *