{"ID":2854114,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15659","arxiv_id":"2510.15659","title":"Magnitude and Phase-based Feature Fusion Using Co-attention Mechanism for Speaker recognition","abstract":"Phase-based features related to vocal source characteristics can be incorporated into magnitude-based speaker recognition systems to improve the system performance. However, traditional feature-level fusion methods typically ignore the unique contributions of speaker semantics in the magnitude and phase domains. To address this issue, this paper proposed a feature-level fusion framework using the co-attention mechanism for speaker recognition. The framework consists of two separate sub-networks for the magnitude and phase domains respectively. Then, the intermediate high-level outputs of both domains are fused by the co-attention mechanism before a pooling layer. A correlation matrix from the co-attention module is supposed to re-assign the weights for dynamically scaling contributions in the magnitude and phase domains according to different pronunciations. Experiments on VoxCeleb showed that the proposed feature-level fusion strategy using the co-attention mechanism gave the Top-1 accuracy of 97.20%, outperforming the state-of-the-art system with 0.82% absolutely, and obtained EER reduction of 0.45% compared to single feature system using FBank.","short_abstract":"Phase-based features related to vocal source characteristics can be incorporated into magnitude-based speaker recognition systems to improve the system performance. However, traditional feature-level fusion methods typically ignore the unique contributions of speaker semantics in the magnitude and phase domains. To add...","url_abs":"https://arxiv.org/abs/2510.15659","url_pdf":"https://arxiv.org/pdf/2510.15659v1","authors":"[\"Rongfeng Su\",\"Mengjie Du\",\"Xiaokang Liu\",\"Lan Wang\",\"Nan Yan\"]","published":"2025-10-17T13:47:44Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}