Uncertainty-Aware Multi-Head Multi-Mode Knowledge Distillation for Self-Supervised Speaker Verification
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 2101-2114
Abstract
No abstract availableFunding Information
- Innovation and Technology Fund of the Hong Kong SAR
- National Key R&D Program of China (2024YFE0217200)
- Research Grants Council of the Hong Kong SAR (15210122)
- Research Grants Council of the Hong Kong SAR (15228223)
This publication has 34 references indexed in Scilit:
- CN-Celeb: Multi-genre speaker recognitionSpeech Communication, 2022
- Contrastive Self-Supervised Learning for Text-Independent Speaker Verification2021
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019
- Squeeze-and-Excitation Networks2018
- CosFace: Large Margin Cosine Loss for Deep Face Recognition2018
- Generalized End-to-End Loss for Speaker Verification2018
- X-Vectors: Robust DNN Embeddings for Speaker Recognition2018
- A study on data augmentation of reverberant speech for robust speech recognition2017
- Deep Residual Learning for Image Recognition2016