How to (Virtually) Train Your Sound Source Localizer - INRIA - Institut National de Recherche en Informatique et en Automatique Access content directly
Preprints, Working Papers, ... (Preprint) Year : 2022

How to (Virtually) Train Your Sound Source Localizer

Abstract

Learning-based methods have become ubiquitous in sound source localization (SSL). Existing systems rely on simulated training sets for the lack of sufficiently large, diverse and annotated real datasets. Most room acoustic simulators used for this purpose rely on the image source method (ISM) because of its computational efficiency. This paper argues that carefully extending the ISM to incorporate more realistic surface, source and microphone responses into training sets can significantly boost the real-world performance of SSL systems. It is shown that increasing the training-set realism of a state-of-the-art direction-of-arrival estimator yields consistent improvements across three different real test sets featuring human speakers in a variety of rooms and various microphone arrays. An ablation study further reveals that every added layer of realism contributes positively to these improvements.
Fichier principal
Vignette du fichier
ICASSP_2023-github_link.pdf (196.29 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03855912 , version 1 (21-11-2022)
hal-03855912 , version 2 (30-11-2022)
hal-03855912 , version 3 (25-05-2023)

Identifiers

  • HAL Id : hal-03855912 , version 2

Cite

Prerak Srivastava, Antoine Deleforge, Archontis Politis, Emmanuel Vincent. How to (Virtually) Train Your Sound Source Localizer. 2022. ⟨hal-03855912v2⟩

Collections

GRID5000 SILECS
163 View
291 Download

Share

Gmail Mastodon Facebook X LinkedIn More