Semantic-Aware Conformer With Multi-Scale Fusion for Speaker Verification
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 4006-4010
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Heilongjiang Province (YQ2024F018)
- National Natural Science Foundation of China (62671220)
This publication has 36 references indexed in Scilit:
- Multi-scale and cardinality-based backbone: toward learning a general-purpose speaker representationInternational Journal of Speech Technology, 2026
- A review of speaker verification: Methods, network architectures, tasks and challengesEngineering Applications of Artificial Intelligence, 2025
- ConFusionformer: Locality-enhanced Conformer through multi-resolution attention fusion for speaker verificationNeurocomputing, 2025
- Progressive channel fusion for more efficient TDNN on speaker verificationSpeech Communication, 2024
- A stacked convolutional neural network framework with multi-scale attention mechanism for text-independent voiceprint recognitionPattern Analysis and Applications, 2024
- MEConformer: Highly representative embedding extractor for speaker verification via incorporating selective convolution into deep speaker encoderExpert Systems with Applications, 2023
- Squeeze-and-Excitation Networks2018
- CosFace: Large Margin Cosine Loss for Deep Face Recognition2018
- Deep Residual Learning for Image Recognition2016
- Deep neural networks for small footprint text-dependent speaker verification2014