Publications
CONFERENCE (INTERNATIONAL) A Study on More Realistic Room Simulation for Far-Field Keyword Spotting
Eric Bezzam (EPFL/Sonos), Robin Scheibler, Cyril Cadoux (EPFL), Thibault Gisselbrecht (Sonos)
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2020 (APSIPA 2020)
December 07, 2020
We investigate the impact of more realistic room simulation for training far-field keyword spotting systems without fine-tuning on in-domain data. To this end, we study the impact of incorporating the following factors in the room impulse response (RIR) generation: air absorption, surface- and frequency-dependent coefficients of real materials, and stochastic ray tracing. Through an ablation study, a wake word task is used to measure the impact of these factors in comparison with a ground-truth set of measured RIRs. On a hold-out set of re-recordings under clean and noisy far-field conditions, we demonstrate up to 35.8% relative improvement over the commonly-used (single absorption coefficient) image source method. Source code is made available in the Pyroomacoustics package, allowing others to incorporate these techniques in their work.
Paper :
A Study on More Realistic Room Simulation for Far-Field Keyword Spotting
(external link)