This paper presents a weighted minimum variance distortionless response (WMVDR) algorithm for far-field sound source localization in a noisy environment. The broadband beam-forming is computed in the frequency-domain by calculating the response power on each frequency bin and by fusing the narrowband components. A machine learning method based on a support vector machine (SVM) is used for selecting only the narrowband components that positively contribute to the broadband fusion. We investigate the direction of arrival (DOA) estimation problem using a uniform linear array (ULA). The skewness measure of response power function is used as input feature for the supervised SVM learning. Simulations demonstrate the effectiveness of the WMVDR in an outdoor noisy environment.

On the use of machine learning in microphone array beamforming for far-field sound source localization

Salvati, Daniele;Drioli, Carlo;Foresti, Gian Luca
2016-01-01

Abstract

This paper presents a weighted minimum variance distortionless response (WMVDR) algorithm for far-field sound source localization in a noisy environment. The broadband beam-forming is computed in the frequency-domain by calculating the response power on each frequency bin and by fusing the narrowband components. A machine learning method based on a support vector machine (SVM) is used for selecting only the narrowband components that positively contribute to the broadband fusion. We investigate the direction of arrival (DOA) estimation problem using a uniform linear array (ULA). The skewness measure of response power function is used as input feature for the supervised SVM learning. Simulations demonstrate the effectiveness of the WMVDR in an outdoor noisy environment.
978-1-5090-0746-2
File in questo prodotto:
File Dimensione Formato  
07738899.pdf

non disponibili

Descrizione: Articolo principale
Tipologia: Documento in Post-print
Licenza: Non pubblico
Dimensione 109.08 kB
Formato Adobe PDF
109.08 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1130392
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 3
social impact