| MuseGAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment HW Dong, WY Hsiao, LC Yang, YH Yang AAAI Conference on Artificial Intelligence, 2018 | 603 | 2018 |
| Convolutional generative adversarial networks with binary neurons for polyphonic music generation HW Dong, YH Yang International Society for Music Information Retrieval Conference, 2018 | 114 | 2018 |
| Pypianoroll: Open source Python package for handling multitrack pianoroll HW Dong, WY Hsiao, YH Yang ISMIR Late-Breaking Demos, 2018 | 56 | 2018 |
| MusPy: A Toolkit for Symbolic Music Generation HW Dong, K Chen, J McAuley, T Berg-Kirkpatrick International Society for Music Information Retrieval Conference, 2020 | 55 | 2020 |
| Automatic melody harmonization with triad chords: A comparative study YC Yeh, WY Hsiao, S Fukayama, T Kitahara, B Genchel, HM Liu, ... Journal of New Music Research 50 (1), 37-51, 2021 | 44 | 2021 |
| On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classification HW Dong, YH Yang arXiv preprint arXiv:1901.08753, 2019 | 36* | 2019 |
| Multitrack Music Transformer HW Dong, K Chen, S Dubnov, J McAuley, T Berg-Kirkpatrick ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 14 | 2023 |
| Deep performer: Score-to-audio music performance synthesis HW Dong, C Zhou, T Berg-Kirkpatrick, J McAuley ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 11 | 2022 |
| Training generative adversarial networks with binary neurons by end-to-end backpropagation HW Dong, YH Yang arXiv preprint arXiv:1810.04714, 2018 | 11 | 2018 |
| MuseGAN: demonstration of a convolutional gan based model for generating multi-track piano-rolls HW Dong, WY Hsiao, LC Yang, YH Yang ISMIR Late-Breaking Demos, 2017 | 11 | 2017 |
| An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition S Edirisooriya, HW Dong, J McAuley, T Berg-Kirkpatrick International Society for Music Information Retrieval Conference, 2021 | 10 | 2021 |
| CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos HW Dong, N Takahashi, Y Mitsufuji, J McAuley, T Berg-Kirkpatrick arXiv preprint arXiv:2212.07065, 2022 | 9 | 2022 |
| Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music HW Dong, C Donahue, T Berg-Kirkpatrick, J McAuley International Society for Music Information Retrieval Conference, 2021 | 5 | 2021 |
| Improving choral music separation through expressive synthesized data from sampled instruments K Chen, HW Dong, Y Luo, J McAuley, T Berg-Kirkpatrick, M Puckette, ... arXiv preprint arXiv:2209.02871, 2022 | 3 | 2022 |
| Equipping Pretrained Unconditional Music Transformers with Instrument and Genre Controls W Xu, J McAuley, S Dubnov, HW Dong arXiv preprint arXiv:2311.12257, 2023 | | 2023 |
| CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models HW Dong, X Liu, J Pons, G Bhattacharya, S Pascual, J Serrą, ... arXiv preprint arXiv:2306.09635, 2023 | | 2023 |
| My research aims to empower music creation with machine learning. I build intelligent systems that learn to compose, arrange and synthesize music. My goal is to lower the … HW Dong | | |
| Flow-based Deep Generative Models J Xu, HW Dong | | |
Yi-Hsuan YangNational Taiwan UniversityVerified email at ntu.edu.tw
