Global–Local Self-Attention Based Transformer for Speaker Verification

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