 Attention and DCT based Global Context Modeling for Text-independent
Speaker RecognitionIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 |
 Adaptive Few-Shot Learning Algorithm for Rare Sound Event DetectionIEEE International Joint Conference on Neural Network (IJCNN), 2022 |
 Speaker Representation Learning using Global Context Guided Channel and
Time-Frequency TransformationsInterspeech (Interspeech), 2020 |
