Liu, T., Das, R. K., Aik Lee, K., & Li, H. (2022). MFA: TDNN with Multi-Scale Frequency-Channel Attention for Text-Independent Speaker Verification with Short Utterances. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9747021
Abstract:
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local frequency region. In addition, the performance of such systems may degrade under short utterance scenarios. To address these issues, we propose a multi-scale frequency-channel attention (MFA), where we characterize speakers at different scales through a novel dual-path design which consists of a convolutional neural network and TDNN. We evaluate the proposed MFA on the VoxCeleb database and observe that the proposed framework with MFA can achieve state-of-the-art performance while reducing parameters and computation complexity. Further, the MFA mechanism is found to be effective for speaker verification with short test utterances.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Feasibility Study Scheme
Grant Reference no. : FS-2021-001
This research / project is supported by the A*STAR - National Robotics Program under Human-Robot Interaction Phase 1
Grant Reference no. : 192 25 00054
This research / project is supported by the A*STAR - RIE2020 Advanced Manufacturing and Engineering Domain (AME)
Grant Reference no. : A1687b0033