A Latently Constrained Mixture Model for Audio Source Separation and Localization

Antoine Deleforge 1 Radu Horaud 1, *
* Corresponding author
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present a method for audio source separation and localization from binaural recordings. The method combines a new generative probabilistic model with time-frequency masking. We suggest that device-dependent relationships between point-source positions and interaural spectral cues may be learnt in order to constrain a mixture model. This allows to capture subtle separation and localization features embedded in the auditory data. We illustrate our method with data composed of two and three mixed speech signals in the presence of reverberations. Using standard evaluation metrics, we compare our method with a recent binaural-based source separation-localization algorithm.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

Contributor : Team Perception <>
Submitted on : Saturday, December 22, 2012 - 6:08:06 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:25 AM
Long-term archiving on : Saturday, March 23, 2013 - 3:47:36 AM


Files produced by the author(s)




Antoine Deleforge, Radu Horaud. A Latently Constrained Mixture Model for Audio Source Separation and Localization. 10th International Conference on Latent Variable Analysis and Signal Separation, Mar 2012, Tel Aviv, Israel. pp.372--379, ⟨10.1007/978-3-642-28551-6_46⟩. ⟨hal-00768660⟩



Record views


Files downloads