Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network

Sharath Adavanne*, Archontis Politis, Tuomas Virtanen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

37 Citations (Scopus)

Abstract

This paper proposes a deep neural network for estimating the directions of arrival (DOA) of multiple sound sources. The proposed stacked convolutional and recurrent neural network (DOAnet) generates a spatial pseudo-spectrum (SPS) along with the DOA estimates in both azimuth and elevation. We avoid any explicit feature extraction step by using the magnitudes and phases of the spectrograms of all the channels as input to the network. The proposed DOAnet is evaluated by estimating the DOAs of multiple concurrently present sources in anechoic, matched and unmatched reverberant conditions. The results show that the proposed DOAnet is capable of estimating the number of sources and their respective DOAs with good precision and generate SPS with high signal-to-noise ratio.

Original languageEnglish
Title of host publication2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO)
PublisherIEEE
Pages1462-1466
Number of pages5
Volume2018-September
ISBN (Print)978-90-827970-1-5
DOIs
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventEuropean Signal Processing Conference - Rome, Italy
Duration: 3 Sep 20187 Sep 2018
Conference number: 26

Publication series

NameEuropean Signal Processing Conference
PublisherIEEE
ISSN (Print)2076-1465
ISSN (Electronic)2076-1465

Conference

ConferenceEuropean Signal Processing Conference
Abbreviated titleEUSIPCO
CountryItaly
CityRome
Period03/09/201807/09/2018

Cite this