Talks

Content

• PhD Defense
• Guest Lectures
• Tutorial Talk
• Invited Talks
• Conference Talks
• Miscellaneous Talks
• Posters

---

PhD Defense

• Generative AI for Music and Audio
  PhD Defense, Department of Computer Science and Engineering, UC San Diego
  La Jolla, CA, USA, May 15, 2024
  slides

---

Guest Lectures

• AI音樂與聲音生成 (AI Music and Audio Generation)
  Guest Lecture, Music Class, Taipei Digital Experimental High School
  Online, May 21, 2024
  slides

• 生成式AI數據庫來源的隱憂 (Concerns of Data Sources for Generative AI)
  Guest Lecture, Topic Exploration, Taipei Digital Experimental High School
  Online, April 29, 2024
  slides

---

Tutorial Talk

• Generating Music with GANs: An Overview and Case Studies
  Hao-Wen Dong and Yi-Hsuan Yang
  Tutorials of the 20th International Society for Music Information Retrieval Conference (ISMIR)
  Delft, The Netherlands, November 4, 2019
  slides

---

Invited Talks

• Towards AI-assisted Video Editing: Generating Shorts from Long Videos
  Embodied Intelligence Seminar, Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology
  Cambridge, MA, September 12, 2025
  slides
• Augmenting Human Creativity with Generative AI
  ECE Seminar, Department of Electrical and Computer Engineering, University of Rochester
  Rochester, NY, March 5, 2025
  slides
• Generative AI for Music: Challenges & Opportunities
  AAAI Workshop on AI for Music
  Philadelphia, PA, March 3, 2025
  slides
• Human-Centered Generative AI for Content Creation: Generating Music and Audio with Machine Learning
  CMSE Colloquium, Department of Computational Mathematics, Science and Engineering, Michigan State University
  East Lansing, MI, January 14, 2025
  slides
• Generative AI for Music and Audio
  CS Colloquium, Department of Computer Science, University of Missouri–St. Louis
  Online, March 7, 2024
  slides
• Learning Text-to-Audio Synthesis from Videos
  Rising Stars in AI Symposium, AI Initiative, King Abdullah University of Science and Technology (KAUST)
  Thuwal, Saudi Arabia, February 20, 2024
  slides
• Generative AI for Music and Audio
  CS Seminar, Department of Computer Science, Northwestern University
  Evanston, IL, USA, November 15, 2023
  slides
• Generative AI for Music and Audio
  Rising Stars in Data Science Workshop, Data Science Institute, University of Chicago
  Chicago, IL, USA, November 14, 2023
  slides
• Generative AI for Music and Audio
  DSP Seminar, Center for Computer Research in Music and Acoustics (CCRMA), Stanford University
  Palo Alto, CA, USA, November 10, 2023
  slides
• Learning Sound Separation and Synthesis from Videos using Pretrained Language-vision Models
  Seminar, Mitsubishi Electric Research Laboratories (MERL)
  Cambridge, MA, USA, October 30, 2023
  slides
• Generative AI for Music and Audio
  Seminar, Institute of Information Science, Academia Sinica
  Taipei, Taiwan, September 18, 2023
  slides

• Generative AI for Music and Audio
  Seminar, Department of Computer Science and Information Engineering, National Taiwan University
  Taipei, Taiwan, September 15, 2023
  slides

• Generative AI for Music and Audio
  Seminar, Graduate Institute of Communication Engineering, National Taiwan University
  Taipei, Taiwan, September 11, 2023
  slides

• Generating Multitrack Music using Deep Learning
  Seminar, AI Research Center, AI Research Center, National Institute of Advanced Industrial Science and Technology (AIST)
  Online, September 12, 2022
  slides
• MusPy: Symbolic Music Processing in Python
  Music + AI Reading Group, Mila and Vector Institute
  Online, April 8, 2022
  slides

• Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
  J. Yang Scholars Symposium, UC San Diego
  Online, September 25, 2021
  slides

• MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment —

  • Music AI Day, Academia Sinica
    Taipei, Taiwan, January 3, 2019
    slides
  • The 28th Generative Music Informatics Workshop
    Hiroshima, Japan, August 20, 2018
    slides
  • The 5th Taiwanese Music and Audio Computing Workshop
    Taipei, Taiwan, May 24, 2018
    slides
  • AAAI Seminar, Program Office of AI Research, Taiwan Ministry of Science and Technology
    Hsinchu, Taiwan, March 24, 2018
    slides

---

Conference Talks

• CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models
  IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
  New Paltz, NY, USA, October 22, 2023
  slides

• CLIPSynth: Learning Text-to-audio Synthesis from Videos using CLIP and Diffusion Models
  CVPR Workshop on Sight and Sound
  Vancouver, Canada, June 19, 2023
  slides

• Multitrack Music Transformer
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  Rhodes, Greece, June 4, 2023
  slides

• CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
  International Conference on Learning Representations (ICLR)
  Kigali, Rwanda, May 1, 2023
  slides

• Deep Performer: Score-to-Audio Music Performance Synthesis
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  Online, May 7, 2022
  slides

• Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
  International Society for Music Information Retrieval Conference (ISMIR)
  Online, November 10, 2021
  slides

• MusPy: A Toolkit for Symbolic Music Generation
  International Society for Music Information Retrieval Conference (ISMIR)
  Online, October 12, 2020
  slides

• Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
  International Society for Music Information Retrieval Conference (ISMIR)
  Paris, France, September 24, 2018
  slides

• MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
  AAAI Conference on Artificial Intelligence (AAAI)
  New Orleans, LA, USA, February 5, 2018
  slides

---

Miscellaneous Talks

• Generating Multitrack Music using Deep Learning
  Group Seminar, Sony Group
  Online, July 1, 2022
  slides
• Convexity & Gradient Descent
  Discussion for Principles of Machine Learning: Learning Algorithms (CSE 251A), UC San Diego
  Online, February 4, 2022
  video  slides  slides
• Empowering Music Creation with Machine Learning
  Thesis Proposal, UC San Diego
  Online, December 9, 2021
  video  slides

• Empower Music Creation with AI
  Group Seminar, Dolby Labs
  Online, August 19, 2021
  slides
• Towards Automatic Instrumentation by Learning to Separate Parts in Multitrack Music
  Research Exam, UC San Diego
  Online, June 8, 2021
  video

• On Unifying Deep Generative Models
  Seminar on Deep Generative Models (CSE 290), UC San Diego
  La Jolla, CA, USA, February 20, 2020
  slides
• Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
  Weekly Seminar, Music and AI Lab, Academia Sinica
  Taipei, Taiwan, October 17, 2018
  slides
• What is Critical in GAN Training?
  Weekly Seminar, Music and AI Lab, Academia Sinica
  Taipei, Taiwan, May 15, 2018
  slides
• Recent Progress on Utilizing Tag Information with GANs
  Weekly Seminar, Music and AI Lab, Academia Sinica
  Taipei, Taiwan, December 26, 2017
  slides
• On Unifying Deep Generative Models
  Weekly Seminar, Music and AI Lab, Academia Sinica
  Taipei, Taiwan, August 15, 2017
  slides
• An Energy-Aware Trust Derivation Scheme With Game Theoretic Approach in Wireless Sensor Networks for IoT Applications
  Weekly Seminar, Wireless Mobile Network Lab, National Taiwan University
  Taipei, Taiwan, November 10, 2016
  slides
• Game Theory for Networks – Learning Algorithms
  Weekly Seminar, Wireless Mobile Network Lab, National Taiwan University
  Taipei, Taiwan, May 2, 2016
  slides

---

Posters

• AcaMate: Supporting Novice A Cappella Singers in Iterative Individual Practice
  Kexin Phyllis Ju, Ting-Yu Pan, and Hao-Wen Dong
  UIST Posters, 2025
  paper  poster

• Learning Text-queried Sound Separation and Synthesis using Unlabeled Videos and Pretrained Language-Vision Models
  Hao-Wen Dong
  Rising Stars in Data Science Workshop, Data Science Institute, University of Chicago
  Chicago, IL, USA, November 14, 2023
  slides
• Learning Text-queried Sound Separation and Synthesis using Unlabeled Videos and Pretrained Language-Vision Models
  Hao-Wen Dong
  Speech and Audio in the Northeast (SANE)
  Brooklyn, NY, USA, October 26, 2023
  slides
• Empowering Music Creation with Machine Learning
  Hao-Wen Dong
  ICASSP Rising Stars in Signal Processing Workshop
  Rhodes, Greece, June 9, 2023
  slides
• Lead sheet and Multi-track Piano-roll generation using MuseGAN
  Hao-Min Liu, Hao-Wen Dong, Wen-Yi Hsiao, and Yi-Hsuan Yang
  GPU Technology Conference Taiwan (GTC Taiwan)
  Taipei, Taiwan, May 30, 2018
  slides