shuqi.
Dai
Computer Science & Music

Shuqi Dai
Computer Science Department
Carnegie Mellon University
Hi, I am a third-year Ph.D. student from Computer Science Department, Carnegie Melon University, advised by Prof. Roger Dannenberg. My research lies in the interection of Computer Music, Machine Learning and Human Computer Interaction, including projects in automatic music generation, music style transfer, music understanding, expressive performance control, human-computer interactive music performance, music technology in music therapy, and Chinese music technology. Before joining CMU, I received my B.S. in Computer Science from Peking University in China in July 2018.
I am also a professional Pipa (Chinese traditional instrument) player with 19 years of performance experience, and a mezzo-soprano with 7-year formal training of Western opera singing. During my bachelor study, I served in PKU Chinese Music Institute (CMI), PKU Musical Club, and Chorus of PKU Hall.
Stylistic Music Generation
Machine Learning, Statistics, MIDI, Serpent, Music Patterns
Proposed and implemented a stylistic music generation system that is able to capture structure, melody, chord progression and bass styles from one or a few example music, and imitate the styles in a new piece using computational techniques, especially statistics and machine learning methods.

Human Computer Music Performance System
Research Project in CMU, Serpent, Wxwidgets, ZMQ
-
HCMP is an emerging computer music system that can perform live music in association with human performers, with goal of creating highly autonomous artificial performers that can fill human roles
-
Introduced new features and refactored old modules for HCMP using Serpent, including virtual time map scheduling, track and channel mapping, and automatic accompaniment; features were used in several live performances
-
Refactored network module to upgrade from ZeroMQ to new, proprietary media communication protocol "Open Sound Control 2" proposed by advisor

Digitalization of Pipa (Traditional Chinese Instrument) Performance Techniques
Python, MIDI, MusicXML
-
Defined first-ever machine-readable symbols for common pipa performance techniques in MusicXML
-
Proposed series of computational models for common pipa performance techniques using "analysis-by-synthesis" method, leading to much more realistic synthesized performances

Friend Machine
Node.js, HTML5/CSS3, PHP
-
Upload a photo of any person, then we will make you a new friend by creating interactively animated faces and emotional interaction
-
Created various animated facial expressions in real-time according to user instructions, based on Facial Feature Point Detection model
-
Operated photo pixels directly on HTML Canvas, so that facial request can be solved in front-end and improved response time dramatically.
-
Used Speech Recognition and Affective Computing models to analyze emotion in user's speaking, and response in both facial expression and voice

Mobile Orchestra (v1.0 Ringtone)
Three-day Personal Workshop Project, SuperCollider, JavaScript, Open Sound Control, Python
-
Developed mobile web app with SuperCollider that lets people use mobile gestures (speeds, ranges, directions) to control melodies (such as ringtones) in real-time as if they were playing musical instruments, adjusting pitch, volume, tempo, accompaniment and special effects etc., allowing group of people to form ringtone orchestra

Seeker
Start-up Project, Dating App, Andriod, Java
-
Seeker is an Andriod application to help people find their Mr./Miss Right and support them date
-
Designed special psychological questionnaires and used Collaborative Filtering algorithm to match people
-
Designed interesting dating process like advancing in games
Publications
-
Shuqi Dai, Huan Zhang, Roger B. Dannenberg. "Automatic Analysis and Influence of Hierarchical Structure on Melody, Rhythm and Harmony in Popular Music". In Proceedings of the 2020 Joint Conference on AI Music Creativity and International Workshop on Music Metacreation (CSMC+MUME), Stockholm, Sweden, Oct 2020. [paper]
-
Z.Wang, K. Chen, J. Jiang, Y. Zhang, M. Xu, Shuqi Dai, X. Gu, G. Xia. "Pop909: A Pop-song Dataset for Music Arrangement Generation". In Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR), Montéal, Canada, 2020. [paper]
-
Gus G. Xia, Shuqi Dai. "Music Style Transfer Issues: A Position Paper". In Proceedings of 6th International Workshop on Music Metacreation (MUME), Salamanca, Spain, June 2018. [paper]
-
Shuqi Dai, Gus G. Xia. "Computational Models For Common Pipa Techniques", best student paper, the 5th National Conference on Sound and Music Technology, Oct 2017.