An Enhanced Res2net With Local And Global Feature Fusion For Speaker Verification

Abstract

Effective fusion of multi-scale features is crucial for improving speaker verification performance. While most existing methods aggregate multi-scale features in a layer-wise manner via simple operations, such as summation or concatenation. This paper proposes a novel architecture called Enhanced Res2Net (ERes2Net), which incorporates both local and global feature fusion techniques to improve the performance. The local feature fusion (LFF) fuses the features within one single residual block to extract the local signal. The global feature fusion (GFF) takes acoustic features of different scales as input to aggregate global signal. To facilitate effective feature fusion in both LFF and GFF, an attentional feature fusion module is employed in the ERes2Net architecture, replacing summation or concatenation operations. A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the ERes2Net in speaker verification. Code has been made publicly available at https:

Stats

• citations50
• S2 citations—
• github stars2919
• HF likes0
• heat score19.74
• arxiv keychen2023an

Related papers

• Eres2netv2: Boosting Short-duration Speaker Verification Performance With Computational Efficiency (2024)9.41
• Unet-based Fusion And Exponential Moving Average Adaptation For Noise-robust Speaker Recognition (2026)0.00
• Interactive Feature Fusion For End-to-end Noise-robust Speech Recognition (2021)12.10
• Interformer: Interactive Local And Global Features Fusion For Automatic Speech Recognition (2023)6.34
• MGFF-TDNN: A Multi-granularity Feature Fusion TDNN Model With Depth-wise Separable Module For Speaker Verification (2025)0.00
• Speakernet: 1D Depth-wise Separable Convolutional Network For Text-independent Speaker Recognition And Verification (2020)0.00
• Gmm-resnext: Combining Generative And Discriminative Models For Speaker Verification (2024)4.52
• Self-attentive Multi-layer Aggregation With Feature Recalibration And Normalization For End-to-end Speaker Verification System (2020)0.00