This paper discusses the application of convolutional neural networks (CNNs) to minimum variance distortionless response localization schemes. We investigate the direction of arrival estimation problems in noisy and reverberant conditions using a uniform linear array (ULA). CNNs are used to process the multichannel data from the ULA and to improve the data fusion scheme, which is performed in the steered response power computation. CNNs improve the incoherent frequency fusion of the narrowband response power by weighting the components, reducing the deleterious effects of those components affected by artifacts due to noise and reverberation. The use of CNNs avoids the necessity of previously encoding the multichannel data into selected acoustic cues with the advantage to exploit its ability in recognizing geometrical pattern similarity. Experiments with both simulated and real acoustic data demonstrate the superior localization performance of the proposed SRP beamformer with respect to other state-of-the-art techniques.

Exploiting CNNs for Improving Acoustic Source Localization in Noisy and Reverberant Conditions

Salvati, Daniele
;
Drioli, Carlo;Foresti, Gian Luca
2018-01-01

Abstract

This paper discusses the application of convolutional neural networks (CNNs) to minimum variance distortionless response localization schemes. We investigate the direction of arrival estimation problems in noisy and reverberant conditions using a uniform linear array (ULA). CNNs are used to process the multichannel data from the ULA and to improve the data fusion scheme, which is performed in the steered response power computation. CNNs improve the incoherent frequency fusion of the narrowband response power by weighting the components, reducing the deleterious effects of those components affected by artifacts due to noise and reverberation. The use of CNNs avoids the necessity of previously encoding the multichannel data into selected acoustic cues with the advantage to exploit its ability in recognizing geometrical pattern similarity. Experiments with both simulated and real acoustic data demonstrate the superior localization performance of the proposed SRP beamformer with respect to other state-of-the-art techniques.
File in questo prodotto:
File Dimensione Formato  
TETCI_ack.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 764.22 kB
Formato Adobe PDF
764.22 kB Adobe PDF Visualizza/Apri
IEEE_TETCI_editoriale_08323305.pdf

non disponibili

Descrizione: Articolo principale
Tipologia: Versione Editoriale (PDF)
Licenza: Non pubblico
Dimensione 933.21 kB
Formato Adobe PDF
933.21 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/11390/1129835
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 36
  • ???jsp.display-item.citation.isi??? ND
social impact