Rectified binaural ratio: A complex T-distributed feature for robust sound localization

Antoine Deleforge 1 Florence Forbes 2
1 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Most existing methods in binaural sound source localization rely on some kind of aggregation of phase-and level-difference cues in the time-frequency plane. While different aggregation schemes exist, they are often heuristic and suffer in adverse noise conditions. In this paper, we introduce the rectified binaural ratio as a new feature for sound source localization. We show that for Gaussian-process point source signals corrupted by stationary Gaussian noise, this ratio follows a complex t-distribution with explicit parameters. This new formulation provides a principled and statistically sound way to aggregate binaural features in the presence of noise. We subsequently derive two simple and efficient methods for robust relative transfer function and time-delay estimation. Experiments on heavily corrupted simulated and speech signals demonstrate the robustness of the proposed scheme.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01372337
Contributor : Antoine Deleforge <>
Submitted on : Tuesday, September 27, 2016 - 10:48:02 AM
Last modification on : Thursday, February 7, 2019 - 4:45:55 PM
Long-term archiving on : Wednesday, December 28, 2016 - 12:59:08 PM

Files

main_studentloc.pdf
Files produced by the author(s)

Identifiers

Citation

Antoine Deleforge, Florence Forbes. Rectified binaural ratio: A complex T-distributed feature for robust sound localization. European Signal Processing Conference, Aug 2016, Budapest, Hungary. pp.1257-1261, ⟨10.1109/EUSIPCO.2016.7760450⟩. ⟨hal-01372337⟩

Share

Metrics

Record views

1202

Files downloads

173