2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSPE-19.1
Paper Title Double Multi-Head Attention for Speaker Verification
Authors Miquel India Massana, Pooyan Safari, Javier Hernando, Universitat Politecnica de Catalunya, Spain
SessionSPE-19: Speaker Recognition 3: Attention and Adversarial
LocationGather.Town
Session Time:Wednesday, 09 June, 14:00 - 14:45
Presentation Time:Wednesday, 09 June, 14:00 - 14:45
Presentation Poster
Topic Speech Processing: [SPE-SPKR] Speaker Recognition and Characterization
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract Most state-of-the-art Deep Learning systems for text-independent speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode variable-length utterances into fixed-length speaker vectors. In this paper we present Double Multi-Head Attention (MHA) pooling, which extends our previous approach based on Self MHA. An additional self attention layer is added to the pooling layer that summarizes the context vectors produced by MHA into a unique speaker representation. This method enhances the pooling mechanism by giving weights to the information captured for each head and it results in creating more discriminative speaker embeddings. We have evaluated our approach with the VoxCeleb2 dataset. Our results show 6.09% and 5.23% relative improvement in terms of EER compared to Self Attention pooling and Self MHA, respectively. According to the obtained results, Double MHA has shown to be an excellent approach to efficiently select the most relevant features captured by the CNN-based front-ends from the speech signal.