Graph Attention Networks For Speaker Verification

Abstract

This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representations of a graph. The proposed framework inputs segment-wise speaker embeddings from an enrollment and a test utterance and directly outputs a similarity score. We first construct a graph using segment-wise speaker embeddings and then input these to graph attention networks. After a few graph attention layers with residual connections, each node is projected into a one-dimensional space using affine transform, followed by a readout operation resulting in a scalar similarity score. To enable successful adaptation for speaker verification, we propose techniques such as separating trainable weights for attention map calculations between segment-wise speaker embeddings from different utterances. The effectiveness of the proposed framework is validated using three different s

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keyjung2020graph

Related papers

• Multi-scale Speaker Embedding-based Graph Attention Networks For Speaker Diarisation (2021)8.35
• Improving Text-independent Speaker Verification With Auxiliary Speakers Using Graph (2021)0.00
• End-to-end Attention Based Text-dependent Speaker Verification (2017)14.87
• Self Multi-head Attention For Speaker Recognition (2019)13.84
• Graph Attentive Feature Aggregation For Text-independent Speaker Verification (2021)6.34
• Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays (2023)0.00
• Exploring A Unified Attention-based Pooling Framework For Speaker Verification (2018)6.77
• Self-attentive Multi-layer Aggregation With Feature Recalibration And Normalization For End-to-end Speaker Verification System (2020)0.00