Global–Local Self-Attention Based Transformer for Speaker Verification

Abstract

Transformer models are now widely used for speech processing tasks due to their powerful sequence modeling capabilities. Previous work determined an efficient way to model speaker embeddings using the Transformer model by combining transformers with convolutional networks. However, traditional global self-attention mechanisms lack the ability to capture local information. To alleviate these problems, we proposed a novel global–local self-attention mechanism. Instead of using local or global multi-head attention alone, this method performs local and global attention in parallel in two parallel groups to enhance local modeling and reduce computational cost. To better handle local location information, we introduced locally enhanced location encoding in the speaker verification task. The experimental results of the VoxCeleb1 test set and the VoxCeleb2 dev set demonstrated the improved effect of our proposed global–local self-attention mechanism. Compared with the Transformer-based Robust Embedding Extractor Baseline System, the proposed speaker Transformer network exhibited better performance in the speaker verification task.