Attention Back-end For Automatic Speaker Verification With Multiple Enrollment Utterances

Abstract

Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of multiple enrollment utterances, we propose a novel attention back-end model, which can be used for both text-independent (TI) and text-dependent (TD) speaker verification, and employ scaled-dot self-attention and feed-forward self-attention networks as architectures that learn the intra-relationships of the enrollment utterances. In order to verify the proposed attention back-end, we conduct a series of experiments on CNCeleb and VoxCeleb datasets by combining it with several sate-of-the-art speaker encoders including TDNN and ResNet. Experimental results using multiple enrollment utterances on CNCeleb show that the proposed attention back-end model leads to lower EER and minDCF score than the PLDA and cosine similarity counterparts for each speaker encoder and an experimen

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keyzeng2021attention

Related papers

• Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00
• Multiobjective Optimization Training Of PLDA For Speaker Verification (2018)2.26
• End-to-end Attention Based Text-dependent Speaker Verification (2017)14.87
• Double Multi-head Attention For Speaker Verification (2020)8.09
• Self Multi-head Attention For Speaker Recognition (2019)13.84
• ECAPA-TDNN: Emphasized Channel Attention, Propagation And Aggregation In TDNN Based Speaker Verification (2020)23.07
• MFA: TDNN With Multi-scale Frequency-channel Attention For Text-independent Speaker Verification With Short Utterances (2022)13.79
• Scoring Of Large-margin Embeddings For Speaker Verification: Cosine Or PLDA? (2022)9.76