| Joint separation and localization of moving sound sources based on neural full-rank spatial covariance analysis H Munakata, Y Bando, R Takeda, K Komatani, M Onishi IEEE Signal Processing Letters 30, 384-388, 2023 | 3 | 2023 |
| Out-of-Vocabulary Word Detection in Spoken Dialogues Based on Joint Decoding with User Response Patterns M Oshio, H Munakata, R Takeda, K Komatani 2023 Asia Pacific Signal and Information Processing Association Annual …, 2023 | 2 | 2023 |
| Multiple-embedding separation networks: Sound class-specific feature extraction for universal sound separation H Munakata, R Takeda, K Komatani 2021 Asia-Pacific Signal and Information Processing Association Annual …, 2021 | 2 | 2021 |
| Training Data Generation with DOA-based Selecting and Remixing for Unsupervised Training of Deep Separation Models H Munakata, R Takeda, K Komatani Proc. Interspeech 2022, 861-865, 2022 | 1 | 2022 |
| Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection T Nishimura, S Nakada, H Munakata, T Komatsu arXiv preprint arXiv:2408.02901, 2024 | | 2024 |
| Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework H Munakata, R Terashima, Y Fujita arXiv preprint arXiv:2406.16315, 2024 | | 2024 |
| Link Prediction Based on Large Language Model and Knowledge Graph Retrieval under Open-World and Resource-Restricted Environment R Takeda, H Munakata, K Komatani | | 2023 |
| Recursive Sound Source Separation with Deep Learning-based Beamforming for Unknown Number of Sources H Munakata, R Takeda, K Komatani Proc. Interspeech 2023, 1688-1692, 2023 | | 2023 |
| TRAINING STRATEGY OF MASSIVE TEXT-TO-AUDIO MODELS AND GPT-BASED QUERY-AUGMENTATION H Munakata, T Nishimura, S Nakada, T Komatsu | | |
Kazunori KomataniProfessor, Osaka University在 sanken.osaka-u.ac.jp 的电子邮件经过验证
