Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
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_ | 1866909620786692096 |
|---|---|
| author | Yaish, Ofir Mishaly, Yehuda Nachmani, Eliya |
| author_facet | Yaish, Ofir Mishaly, Yehuda Nachmani, Eliya |
| contents | We introduce a new paradigm for active sound modification: Active Speech Enhancement (ASE). While Active Noise Cancellation (ANC) algorithms focus on suppressing external interference, ASE goes further by actively shaping the speech signal -- both attenuating unwanted noise components and amplifying speech-relevant frequencies -- to improve intelligibility and perceptual quality. To enable this, we propose a novel Transformer-Mamba-based architecture, along with a task-specific loss function designed to jointly optimize interference suppression and signal enrichment. Our method outperforms existing baselines across multiple speech processing tasks -- including denoising, dereverberation, and declipping -- demonstrating the effectiveness of active, targeted modulation in challenging acoustic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16911 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation Yaish, Ofir Mishaly, Yehuda Nachmani, Eliya Audio and Speech Processing Artificial Intelligence We introduce a new paradigm for active sound modification: Active Speech Enhancement (ASE). While Active Noise Cancellation (ANC) algorithms focus on suppressing external interference, ASE goes further by actively shaping the speech signal -- both attenuating unwanted noise components and amplifying speech-relevant frequencies -- to improve intelligibility and perceptual quality. To enable this, we propose a novel Transformer-Mamba-based architecture, along with a task-specific loss function designed to jointly optimize interference suppression and signal enrichment. Our method outperforms existing baselines across multiple speech processing tasks -- including denoising, dereverberation, and declipping -- demonstrating the effectiveness of active, targeted modulation in challenging acoustic environments. |
| title | Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2505.16911 |