Abstract
Accurate direction-of-arrival (DOA) estimation in noisy and reverberant environments is a long-standing challenge in the field of acoustic signal processing. One of the promising research directions utilizes the decomposition of the multimicrophone measurements into the spherical harmonics (SH) domain. This paper presents an evaluation and comparison of learning-based single-source DOA estimation using two recently introduced SH domain features denoted relative harmonic coefficients (RHC) and relative modal coherence (RMC), respectively. Both features were shown to be independent of the time-varying source signal even in reverberant environments, thus facilitating training with synthesized, continuously-active, noise signal rather than with speech signal. The inspected features are fed into a convolutional neural network, trained as a DOA classifier. Extensive validations confirm that the RHC-based method outperforms the RMC-based method, especially under unfavorable scenarios with severe noise and reverberation.
Original language | English |
---|---|
Title of host publication | 30th European Signal Processing Conference, EUSIPCO 2022 - Proceedings |
Publisher | European Signal Processing Conference, EUSIPCO |
Pages | 329-333 |
Number of pages | 5 |
ISBN (Electronic) | 9789082797091 |
State | Published - 2022 |
Event | 30th European Signal Processing Conference, EUSIPCO 2022 - Belgrade, Serbia Duration: 29 Aug 2022 → 2 Sep 2022 |
Publication series
Name | European Signal Processing Conference |
---|---|
Volume | 2022-August |
ISSN (Print) | 2219-5491 |
Conference
Conference | 30th European Signal Processing Conference, EUSIPCO 2022 |
---|---|
Country/Territory | Serbia |
City | Belgrade |
Period | 29/08/22 → 2/09/22 |
Bibliographical note
Publisher Copyright:© 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.
Keywords
- Learning-based direction-of-arrival estimation
- relative harmonic coefficients
- relative modal coherence