1. Domain Generalized Speaker Embedding Learning via Mutual Information Minimization;hyun kang;Proc The Speaker and Language Recognition Workshop (Odyssey 2022),0
2. Club: A contrastive log-ratio upper bound of mutual information;cheng;ArXiv Preprint,2020
3. Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
4. Improving zero-shot voice style transfer via disentangled representation learning;yuan;International Conference on Learning Representations,0