Linearly Constrained Deep Beamformer for Multi-Speaker Scenarios
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913149443112960 |
|---|---|
| author | Zaidel, Ilai Engel, Ori Engel, Bar Gannot, Sharon |
| author_facet | Zaidel, Ilai Engel, Ori Engel, Bar Gannot, Sharon |
| contents | We propose a deep beamforming framework for enhancing target speaker(s) in multi-speaker environments. A deep neural network (DNN) is trained to estimate beamforming weights directly from noisy multichannel inputs while satisfying linear spatial constraints through an adaptive multi-term loss inspired by the augmented Lagrangian framework. The loss combines signal reconstruction with penalties that enforce a distortionless response toward the target and suppress the interference subspace. The model is further guided by the target relative transfer function (RTF) and the estimated interference subspace. The proposed model can direct a beam toward the target speaker while directing nulls toward the interfering sources, achieving superior overall enhancement performance compared with the classical LCMV beamformer constructed by the same estimated spatial signatures. Furthermore, compared with the LCMV beamformer, the proposed model produces more controlled sidelobes and improved background-noise attenuation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21141 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Linearly Constrained Deep Beamformer for Multi-Speaker Scenarios Zaidel, Ilai Engel, Ori Engel, Bar Gannot, Sharon Audio and Speech Processing We propose a deep beamforming framework for enhancing target speaker(s) in multi-speaker environments. A deep neural network (DNN) is trained to estimate beamforming weights directly from noisy multichannel inputs while satisfying linear spatial constraints through an adaptive multi-term loss inspired by the augmented Lagrangian framework. The loss combines signal reconstruction with penalties that enforce a distortionless response toward the target and suppress the interference subspace. The model is further guided by the target relative transfer function (RTF) and the estimated interference subspace. The proposed model can direct a beam toward the target speaker while directing nulls toward the interfering sources, achieving superior overall enhancement performance compared with the classical LCMV beamformer constructed by the same estimated spatial signatures. Furthermore, compared with the LCMV beamformer, the proposed model produces more controlled sidelobes and improved background-noise attenuation. |
| title | Linearly Constrained Deep Beamformer for Multi-Speaker Scenarios |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2605.21141 |