Resources

Content

• Teaching
• Datasets
• Toolkits
• Faculty Job Search Material
• Proposals
• Statements
• Rejections

---

Teaching Materials

• Music & AI (PAT 463/563, University of Michigan, Fall 2025 version)
• Creative Coding (PAT 204/504, University of Michigan, Fall 2025 version)

---

Datasets

• Open Screen Soundtrack Library (OSSL) — A collection of 36.5 hours of public-domain or CC-licensed movie clips, paired with high-quality soundtracks and human-annotated mood information
• Bach Violin Dataset — A collection of high-quality public recordings of Bach’s sonatas and partitas for solo violin (BWV 1001–1006)
• Lakh Pianoroll Dataset (LPD) — A collection of 174,154 multitrack pianorolls derived from the MIDI files in Lakh MIDI Dataset

---

Toolkits

• MusPy — A Toolkit for Symbolic Music Generation
  code  documentation  PYPI
• PyPianoroll — A Python package for handling multitrack pianorolls
  code  documentation  PYPI

---

Faculty Job Search Material

Here is the application package for my faculty job search in 2023 (for Fall 2024 positions):

• CV
• Research Statement
• Teaching Statement
• EDI Statement

---

Proposals

• Proposal for NVIDIA Academic Grant Program (2025) – “Teaser Generation for Long Documentaries and Educational Videos”
• Abstract & Proposal (in Chinese) for Taiwan’s Government Scholarship to Study Abroad (2022) – “Deep Musician: Multi-instrument Music Composition and Performance Synthesis using Deep Learning”

---

Statements

• Statement for AAAI New Faculty Highlights (2026)
• Research Statement for Rising Stars in Data Science (2023)
• Statement for Friends of International Center Fellowship (2023)
• Research Statement for ICASSP Rising Stars in Signal Processing (2023)
• Research Statement for UCSD GPSA Interdisciplinary Research Award (2023)
• Statement of Purpose for PhD transfer to the CSE program at UC San Diego (2020)
• Statement of Purpose for PhD application to the ECE program at UC San Diego (2019)

---

Rejections

• Generating Symbolic Music from Natural Language Prompts using an LLM-Enhanced Dataset
  Weihan Xu, Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov, and Hao-Wen Dong
  International Society for Music Information Retrieval Conference (ISMIR), 2025
  paper  demo  poster  code  reviews

  • Rejected by ICASSP (2025)  reviews
  • Rejected by ISMIR (2024)  reviews

• Synthesizing Composite Hierarchical Structure from Symbolic Music Corpora
  Ilana Shapiro, Ruanqianqian Huang, Zachary Novack, Cheng-I Wang, Hao-Wen Dong, Taylor Berg-Kirkpatrick, Shlomo Dubnov, and Sorin Lerner
  International Joint Conference on Artificial Intelligence (IJCAI), AI, Arts & Creativity Track, 2025
  paper  code

  • Rejected by AAAI (2025)  reviews

• FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval
  Junda Wu, Zachary Novack, Amit Namburi, Hao-Wen Dong, Caron Chen, Zhouhang Xie, Jiaheng Dai, and Julian McAuley
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
  paper  demo  reviews

  • Rejected by ISMIR (2024)  reviews

• CLIPSynth: Learning Text-to-audio Synthesis from Videos using CLIP and Diffusion Models
  Hao-Wen Dong, Gunnar A. Sigurdsson, Chenyang Tao, Jiun-Yu Kao, Yu-Hsiang Lin, Anjali Narayan-Chen, Arpit Gupta, Tagyoung Chung, Jing Huang, Nanyun Peng, and Wenbo Zhao
  CVPR Workshop on Sight and Sound (WSS), 2023
  paper  demo  video  slides

  • Rejected by MMSP (2023)  reviews
  • Rejected by ICML (2023)  reviews

• Multitrack Music Transformer
  Hao-Wen Dong, Ke Chen, Shlomo Dubnov, Julian McAuley, and Taylor Berg-Kirkpatrick
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
  paper  demo  video  slides  code  reviews

  • Rejected by ISMIR (2022)  reviews

• On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classification
  Hao-Wen Dong and Yi-Hsuan Yang
  arXiv preprint arXiv:1901.08753, 2019
  paper  demo  code

  • Rejected by JMLR (2022)  reviews
  • Rejected by IJCV (2019)  reviews
  • Rejected by ICML (2018)  reviews

• Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
  Hao-Wen Dong and Yi-Hsuan Yang
  arXiv preprint arXiv:1810.04714, 2018
  paper  demo  slides  code

  • Rejected by ICMLA (2018)  reviews