An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancement
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_ | 1866913923736797184 |
|---|---|
| author | Ho, Chun-Wei Ku, Pin-Jui Yen, Hao Siniscalchi, Sabato Marco Tsao, Yu Lee, Chin-Hui |
| author_facet | Ho, Chun-Wei Ku, Pin-Jui Yen, Hao Siniscalchi, Sabato Marco Tsao, Yu Lee, Chin-Hui |
| contents | We propose a novel iterative phase estimation framework, termed multi-source Griffin-Lim algorithm (MSGLA), for speech enhancement (SE) under additive noise conditions. The core idea is to leverage the ad-hoc consistency constraint of complex-valued short-time Fourier transform (STFT) spectrograms to address the sign ambiguity challenge commonly encountered in geometry-based phase estimation. Furthermore, we introduce a variant of the geometric constraint framework based on the law of sines and cosines, formulating a new phase reconstruction algorithm using noise phase estimates. We first validate the proposed technique through a series of oracle experiments, demonstrating its effectiveness under ideal conditions. We then evaluate its performance on the VB-DMD and WSJ0-CHiME3 data sets, and show that the proposed MSGLA variants match well or slightly outperform existing algorithms, including direct phase estimation and DNN-based sign prediction, especially in terms of background noise suppression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02192 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancement Ho, Chun-Wei Ku, Pin-Jui Yen, Hao Siniscalchi, Sabato Marco Tsao, Yu Lee, Chin-Hui Audio and Speech Processing We propose a novel iterative phase estimation framework, termed multi-source Griffin-Lim algorithm (MSGLA), for speech enhancement (SE) under additive noise conditions. The core idea is to leverage the ad-hoc consistency constraint of complex-valued short-time Fourier transform (STFT) spectrograms to address the sign ambiguity challenge commonly encountered in geometry-based phase estimation. Furthermore, we introduce a variant of the geometric constraint framework based on the law of sines and cosines, formulating a new phase reconstruction algorithm using noise phase estimates. We first validate the proposed technique through a series of oracle experiments, demonstrating its effectiveness under ideal conditions. We then evaluate its performance on the VB-DMD and WSJ0-CHiME3 data sets, and show that the proposed MSGLA variants match well or slightly outperform existing algorithms, including direct phase estimation and DNN-based sign prediction, especially in terms of background noise suppression. |
| title | An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancement |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.02192 |