Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 International Journal of Microelectronics and Computer Science

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Combining Multiple Sound Sources Localization Hybrid Algorithm and Fuzzy Rule Based Classification for Real-time Speaker Tracking Application

Ibala C, Astapov S, Bettens F, Escobar F, Chang X, Valderrama C, Riid A

International Journal of Microelectronics and Computer Science

2013

Vol. 4, nr 1

12--25

This work present a novel approach to track a specific speaker among multiple using the Minimum Variance Distortionless Response (MVDR) beamforming and fuzzy logic ruled based classification for speaker recognition. The Sound sources localization is performed with an improve delay and sum beamforming (DSB) computation methodology. Our proposed hybrid algorithm computes first the Generalized Cross Correlation (GCC) to create a reduced search spectrum for the DSB algorithm. This methodology reduces by more than 70% the DSB localization computation burden. Moreover for high frequencies Sound sources beamforming, the DSB will be preferred to the MVDR for logic and power consumption reduction.

Hybrid Algorithm Computation Methodology to Accelerate Sound Source Localization

Ibala C., Escobar F., Chanang X., Valderrama C. C.

International Journal of Microelectronics and Computer Science

2012

Vol. 3, nr 3

99-110

Latest algorithm solutions for sound source localization have dramatically increased their computation burden. This paper proposes a novel hybrid algorithm with the ability to adapt its search spectrum based on target movement; we also show some studies and metrics to analyze its implementation constraints and remark its advantages over previous solutions. The proposed algorithm provides a good balance between processing power and real-time execution; our approach combines the General Cross Correlation (GCC) with the Delay and Sum Beamforming (DSB) algorithm, such that, less than 50% of thee DSB computation is necessary to locate the sound source.