Structured Sparsity for Sound Field Reproduction with Overlapping Groups: Investigation of the Latent Group Lasso

Gauthier PA, Grandjean P, Berry Alain. Structured Sparsity for Sound Field Reproduction with Overlapping Groups: Investigation of the Latent Group Lasso. In: AES Conference: 2018 AES International Conference on Spatial Reproduction - Aesthetics and Science. Audio Engineering Society; 2018. Paper P9-1. Available from: https://aes.org/publications/elibrary-page/?id=19627

@inproceedings{Gauthier2018_19627,
  author = {Gauthier, Philippe-Aubert and Grandjean, Pierre and {Berry Alain}},
  title = {{Structured Sparsity for Sound Field Reproduction with Overlapping Groups: Investigation of the Latent Group Lasso}},
  booktitle = {AES Conference: 2018 AES International Conference on Spatial Reproduction - Aesthetics and Science},
  note = {Paper P9-1},
  year = {2018},
  month = jul,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19627}
}

TY  - CPAPER
TI  - Structured Sparsity for Sound Field Reproduction with Overlapping Groups: Investigation of the Latent Group Lasso
AU  - Gauthier, Philippe-Aubert
AU  - Grandjean, Pierre
AU  - Berry Alain
T2  - AES Conference: 2018 AES International Conference on Spatial Reproduction - Aesthetics and Science
M1  - Paper P9-1
PY  - 2018
DA  - 2018/07/06
UR  - https://aes.org/publications/elibrary-page/?id=19627
PB  - Audio Engineering Society
LA  - en
AB  - Sound ?eld reproduction (SFR) applied to microphone array recordings can be de?ned as an inverse problem. A typical issue is the resulting spatial source signal distribution. A least-square approach with solution 2-norm regularization will activate all sources. To circumvent such issues, sparsity-based regularization offers promising advantages. However, this can result in too sparse solutions. A promising avenue is based on structured-sparsity for prede?ned groups of reproduction sources. To this end, the group lasso was recently investigated without overlapping group. Its inability to deal with overlapping groups is a limitation. This paper presents the latent group lasso (LGL) where group-level sparsity is induced for overlapping groups. Theoretical results of LGL are successfully compared to other SFR results for sparsity-inducing norms.
ER  -