Realistic sources, receivers and walls improve the generalisability of virtually-supervised blind acoustic parameter estimators - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Realistic sources, receivers and walls improve the generalisability of virtually-supervised blind acoustic parameter estimators

Abstract

Blind acoustic parameter estimation consists in inferring the acoustic properties of an environment from recordings of unknown sound sources. Recent works in this area have utilized deep neural networks trained either partially or exclusively on simulated data, due to the limited availability of real annotated measurements. In this paper, we study whether a model purely trained using a fast image-source room impulse response simulator can generalize to real data. We present an ablation study on carefully crafted simulated training sets that account for different levels of realism in source, receiver and wall responses. The extent of realism is controlled by the sampling of wall absorption coefficients and by applying measured directivity patterns to microphones and sources. A state-of-the-art model trained on these datasets is evaluated on the task of jointly estimating the room's volume, total surface area, and octave-band reverberation times from multiple, multichannel speech recordings. Results reveal that every added layer of simulation realism at train time significantly improves the estimation of all quantities on real signals.
Fichier principal
Vignette du fichier
2207.09133.pdf (385.63 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03727423 , version 1 (30-09-2022)

Identifiers

  • HAL Id : hal-03727423 , version 1

Cite

Prerak Srivastava, Antoine Deleforge, Emmanuel Vincent. Realistic sources, receivers and walls improve the generalisability of virtually-supervised blind acoustic parameter estimators. 17th International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2022, Bamberg, Germany. ⟨hal-03727423⟩
59 View
68 Download

Share

Gmail Facebook Twitter LinkedIn More