P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Preprint
Abstract
Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV). Both of them have advantages and disadvantages from the perspective of global and local feature modeling. How to effectively integrate these two style features is still an open issue. In this paper, we explore a Parallel-coupled TDNN/Transformer Network (p-vectors) to replace the serial hybrid networks. The p-vectors allows TDNN and Transformer to learn the complementary information from each other through Soft Feature Alignment Interaction (SFAI) under the premise of preserving local and global features. Also, p-vectors uses the Spatial Frequency-channel Attention (SFA) to enhance the spatial interdependence modeling for input features. Finally, the outputs of dual branches of p-vectors are combined by Embedding Aggregation Layer (EAL). Experiments show that p-vectors outperforms MACCIF-TDNN and MFA-Conformer with relative improvements of 11.5% and 13.9% in EER on VoxCeleb1-O.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- LayerCAM: Exploring Hierarchical Class Activation Maps for LocalizationIEEE Transactions on Image Processing, 2021
- Speaker-Utterance Dual Attention for Speaker and Utterance Verification2020
- Self-Attention Encoding and Pooling for Speaker Recognition2020
- An Effective Deep Embedding Learning Architecture for Speaker Verification2019
- Res2Net: A New Multi-Scale Backbone ArchitectureIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- VoxCeleb2: Deep Speaker Recognition2018
- VoxCeleb: A Large-Scale Speaker Identification Dataset2017
- Analysis of Score Normalization in Multilingual Speaker Recognition2017
- Front-End Factor Analysis for Speaker VerificationIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989