Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918099063668736 |
|---|---|
| author | Wang, Zhong-Qiu Pang, Ruizhe |
| author_facet | Wang, Zhong-Qiu Pang, Ruizhe |
| contents | In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target speech. With this observation, we propose to leverage beamformed mixture, which has a higher SNR of the target speaker than the input mixture, as a weak supervision to train deep neural networks (DNNs) to enhance the input mixture. This way, we can train enhancement models using pairs of real-recorded mixture and its beamformed mixture, and potentially realize better generalization to real mixtures, compared with only training the models on simulated mixtures, which usually mismatch real mixtures. Evaluation results on the real-recorded CHiME-4 dataset show the effectiveness of the proposed algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15229 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR Wang, Zhong-Qiu Pang, Ruizhe Audio and Speech Processing In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target speech. With this observation, we propose to leverage beamformed mixture, which has a higher SNR of the target speaker than the input mixture, as a weak supervision to train deep neural networks (DNNs) to enhance the input mixture. This way, we can train enhancement models using pairs of real-recorded mixture and its beamformed mixture, and potentially realize better generalization to real mixtures, compared with only training the models on simulated mixtures, which usually mismatch real mixtures. Evaluation results on the real-recorded CHiME-4 dataset show the effectiveness of the proposed algorithm. |
| title | Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.15229 |