Multi-scale aggregation of phase information for complexity reduction of CNN based DOA estimation

Chakrabarty S, Habets E (2019)

Publication Type: Conference contribution

Publication year: 2019

Publisher: European Signal Processing Conference, EUSIPCO

Book Volume: 2019-September

Conference Proceedings Title: European Signal Processing Conference

Event location: A Coruna ES

ISBN: 9789082797039

DOI: 10.23919/EUSIPCO.2019.8903176

Abstract

In a recent work on direction-of-arrival (DOA) estimation of multiple speakers with convolutional neural networks (CNNs), the phase component of short-time Fourier transform (STFT) coefficients of the microphone signal is given as input and small filters are used to learn the phase relations between neighboring microphones. Due to the chosen filter size, M − 1 convolution layers are required to achieve the best performance for a microphone array with M microphones. For arrays with large number of microphones, this requirement leads to a high computational cost making the method practically infeasible. In this work, we propose to expand the receptive field of the filters to reduce the computational cost of our previously proposed method. To realize this expansion, we use systematic dilations of the filters in each of the convolution layers. Different systematic dilation strategies for a specific microphone array are explored. Experimental analysis of the different strategies, shows that an aggressive expansion strategy results in a considerable reduction in computational cost while a relatively gradual expansion of the receptive field exhibits the best DOA estimation performance along with reduction in the computational cost.

Authors with CRIS profile

Soumitro Chakrabarty International Audio Laboratories Erlangen (AudioLabs) Emanuël Habets Professur für wahrnehmungsbasierte räumliche Audiosignalverarbeitung (AudioLabs) (Stiftungsprofessur)

How to cite

APA:

Chakrabarty, S., & Habets, E. (2019). Multi-scale aggregation of phase information for complexity reduction of CNN based DOA estimation. In European Signal Processing Conference. A Coruna, ES: European Signal Processing Conference, EUSIPCO.

MLA:

Chakrabarty, Soumitro, and Emanuël Habets. "Multi-scale aggregation of phase information for complexity reduction of CNN based DOA estimation." Proceedings of the 27th European Signal Processing Conference, EUSIPCO 2019, A Coruna European Signal Processing Conference, EUSIPCO, 2019.

BibTeX: Download