Music can touch the hearts of any audience without them possessing
any knowledge of its context. The power of music is transcendental, and it stems from
the timbre of the instrument(s), the fundamental rhythmic structure and melody, the
dynamics, instrumentation, and many more, all of which cooperate in some form of harmony
to create the final product. With the recent rise of Artificial Intelligence-Generated
Contents (AIGC), AI for music is a promising field full of creativity, novel
methodologies, and technologies that are yet to be explored. Currently, AI for music
methods have been commonly concentrated on utilizing machine learning and deep learning
techniques to generate new music. Despite the significant milestones that have been
achieved thus far, many are not necessarily robust for a wide range of applications.
AI music itself is a timely topic. This workshop aims to generate momentum around this
topic of growing interest, and to encourage interdisciplinary interaction and
collaboration between AI, music, Natural Language Processing (NLP),
machine learning, multimedia,
Human-Computer Interaction (HCI), audio processing, computational
linguistics, and neuroscience.
It serves as a forum to bring together active researchers and practitioners from
academia and industry to share their recent advances in this promising area.
Dec. 17, 2023, Italy (GMT+1)
Virtually: Please join IEEE Big Data Workshop - AIMG 2023 using your paper author information.
Physically: Hilton Sorrento Palace, Conference Room - Ravello
| Paper Title | Author(s) | |
| Session I (Italy Time 14:00-14:50) | ||
| Opening Remarks | ||
| Musical Elements Enhancement and Image Content Preservation Network for Image to Music Generation | Wenzhao Liu and Dechao Meng | |
| AI Music Showcase | ||
| Things, Objects, Subjects and Stuff: IoMuSt and Ubimus Perspectives on AI | Marcello Messina and Luzilei Aliel | |
| Session II (Italy Time 14:50-16:20) | ||
| Equipping Pretrained Unconditional Music Transformers with Instrument and Genre Controls | Weihan Xu, Julian McAuley, Shlomo Dubnov, and Hao-Wen Dong | |
| Automatic Time Signature Determination for New Scores Using Lyrics for Latent Rhythmic Structure | Callie Liao, Duoduo Liao, and Jesse Guessford | |
| AI-Algorithmically-Generated Song with Lyrics | Callie Liao and Duoduo Liao | |
| AI Music Showcase | ||
| Music Generation using Human-In-The-Loop Reinforcement Learning | Aju Ani Justus | |
| Music Generation Using Deep Learning | Shanmukh Krishna B, Satya Sai Roopa Sree Chiluvuri, Sai Sri Harshini Kosuri, Sai Sree Harsha Chimbili, and Mahima Agumbe Suresh | |
| Session III (Italy Time 16:20-17:30) | ||
| Snake in the Labyrinth: Scenes from the Machine’s Deep Q-Learning Experience | Jeffrey Morris | |
| AI Music Showcase | ||
| Let the "Perfect Voice" Always Be There, Positive Affirmation and Negative Anxiety from Online Commentary | Yingzixuan Zhang, Kaixuan Niu, and Zhian Zhao | |
| AI Music Showcase | ||
| Keynote: The Importance of Working with a Musician in AI Music Prof. Jesse Guessford, George Mason University |
||
| Closing Remarks & Award Announcements | ||
*The program schedule is subject to change.
Submission and notification dates:
Acceptance notifications and review reports were sent via email.
Final camera-ready submission dates:
If you are participating virtually and are unable to give a live presentation on Zoom, you must attend the session to answer questions from the audience. Please upload your video (.mp4) to the main conference by Dec. 3rd.
