Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances Y Jung, S Kye, Y Choi, M Jung, H Kim Interspeech 2020, 2020 | 45 | 2020 |
Multi-task network for noise-robust keyword spotting and speaker verification using CTC-based soft VAD and global query attention M Jung, Y Jung, J Goo, H Kim Interspeech 2020, 931-935, 2020 | 19 | 2020 |
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings M Jung, H Lim, J Goo, Y Jung, H Kim 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019 | 17 | 2019 |
Dynamic noise embedding: Noise aware training and adaptation for speech enhancement J Lee, Y Jung, M Jung, H Kim 2020 Asia-Pacific Signal and Information Processing Association Annual …, 2020 | 15 | 2020 |
Learning acoustic word embeddings with phonetically associated triplet network H Lim, Y Kim, Y Jung, M Jung, H Kim arXiv preprint arXiv:1811.02736, 2018 | 5 | 2018 |
Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings M Jung, H Kim Interspeech 2022, 5170-5174, 2022 | 3 | 2022 |
AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination M Jung, H Kim Interspeech 2023, 2023 | 1 | 2023 |
Triplet loss based domain adversarial training for robust wake-up word detection in noisy environments H Lim, M Jung, H Kim The Journal of the Acoustical Society of Korea 39 (5), 468-475, 2020 | | 2020 |