{"ID":2899407,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02192","arxiv_id":"2507.02192","title":"An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancement","abstract":"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.","short_abstract":"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 a...","url_abs":"https://arxiv.org/abs/2507.02192","url_pdf":"https://arxiv.org/pdf/2507.02192v1","authors":"[\"Chun-Wei Ho\",\"Pin-Jui Ku\",\"Hao Yen\",\"Sabato Marco Siniscalchi\",\"Yu Tsao\",\"Chin-Hui Lee\"]","published":"2025-07-02T23:01:59Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}