ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
This work addresses the challenge of efficient and accurate speaker verification for applications like biometric security, though it appears incremental as it builds on existing attention-based methods.
The paper tackles the problem of speaker verification by proposing ACA-Net, a lightweight model that uses Asymmetric Cross Attention to replace temporal pooling, achieving a 5% relative improvement in Equal Error Rate on the WSJ0-1talker dataset with only one-fifth of the parameters compared to a strong baseline.
In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling. ACA is able to distill large, variable-length sequences into small, fixed-sized latents by attending a small query to large key and value matrices. In ACA-Net, we build a Multi-Layer Aggregation (MLA) block using ACA to generate fixed-sized identity vectors from variable-length inputs. Through global attention, ACA-Net acts as an efficient global feature extractor that adapts to temporal variability unlike existing SV models that apply a fixed function for pooling over the temporal dimension which may obscure information about the signal's non-stationary temporal variability. Our experiments on the WSJ0-1talker show ACA-Net outperforms a strong baseline by 5\% relative improvement in EER using only 1/5 of the parameters.