Frequency map selection using a RBFN-based classifier in the MVDR beamformer for speaker localization in reverberant rooms

Salvati, Daniele; Drioli, Carlo; Foresti, Gian Luca

CINECA IRIS Institutional Research Information System

IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.

We present the weighted minimum variance distortionless response (WMVDR), which is a steered response power (SRP) algorithm, for near-field speaker localization in a reverberant environment. The proposed WMVDR is based on a machine learning approach for computing the incoherent frequency fusion of narrowband power maps. We adopt a radial basis function network (RBFN) classifier for the estimation of the weighting coefficients, and a marginal distribution of narrowband power map as feature for the supervised training operation. Simulations demonstrate the effectiveness of the proposed approach in different conditions

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11390/1103912

Titolo:	Frequency map selection using a RBFN-based classifier in the MVDR beamformer for speaker localization in reverberant rooms
Autori:	Salvati, Daniele DRIOLI, Carlo FORESTI, Gian Luca mostra contributor esterni nascondi contributor esterni
Data di pubblicazione:	2015
Serie:	INTERSPEECH
Abstract:	We present the weighted minimum variance distortionless response (WMVDR), which is a steered response power (SRP) algorithm, for near-field speaker localization in a reverberant environment. The proposed WMVDR is based on a machine learning approach for computing the incoherent frequency fusion of narrowband power maps. We adopt a radial basis function network (RBFN) classifier for the estimation of the weighting coefficients, and a marginal distribution of narrowband power map as feature for the supervised training operation. Simulations demonstrate the effectiveness of the proposed approach in different conditions
Handle:	http://hdl.handle.net/11390/1103912
Appare nelle tipologie:	4.1 Contributo in Atti di convegno

File in questo prodotto:

File	Descrizione	Tipologia	Licenza
FreqMapSelection_finalProceedings.pdf	Articolo principale	Post-print	Non pubblico	Accesso ristretto Richiedi una copia

Citazioni

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