Section: New Software and Platforms

Supervised Binaural Mapping Software

Functional Description

Figure 2. An audio-visual sound source (left) that emits white noise is moved in front of the POPEYE robot (middle). These input-output observation pairs are used to estimate a regression function that is then used to predict the location of a sound (right).

The SBM Matlab toolbox for “Supervised Binaural Mapping", contains a set of functions and scripts for supervised binaural sound source separation and localization. The approach consists in learning the acoustic space of a system using a set of white-noise measurements. Once the acoustic space is learned, it can be used to efficiently localize one or several natural sound sources such as speech, and to separate their signals.

• Participants: Antoine Deleforge, Soraya Arias and Radu Horaud

• Contact: Radu Horaud

• URL: https://team.inria.fr/perception/supervised-binaural-mapping/