본문 바로가기

Music & Audio Technology

Data Sonification Ensemble (with Chris Chafe, Robyn Schulkowsky, Joey Baron) We performed at Bing Concert Hall for the 50th Anniversary Concert of CCRMA, Stanford. The Days, The Conversation and The Dallas Thermidor (2024) The Sonification Ensemble | Ray Du, morin khuur | Soohyun Kim, guitar | Garrett Kukier, guitar | Kevin Wenkai Liao, banjo | Rinseo Park, tiny cymbals & tympany | Tristan Peng, piano | Andrew James Sung, cello | Rochelle Tham, computer sound | Leaf Ye, .. 더보기
Stanford x Berkeley Academic Networking [History of Music Technology Research at Stanford University] I gave a talk at Samsung Semiconductor (San Jose campus) for [Stanford x Berkeley Academic Conference & Networking]. 더보기
PINN - DSP Seminar at CCRMA (Stanford) I did a seminar at CCRMA, Stanford University, on [PINN (Physics Informed Neural Network) for Physical Modeling]. PINN is recently ongoing research on using a neural network as a differential equation solver by explicitly integrating the differential equation itself and the boundary conditions into the loss function. Recently, PINN and its variants have gotten attention mostly for fluid modeling.. 더보기
CTP431 Guest Lecture at KAIST I gave a guest lecture at KAIST for [CTP431: Fundamentals of Computer Music] (Prof. Juhan Nam). Topic: Introduction to ChucK — Interactive computer music performance, audio-visual graphics, interactive AI, web audio, and sound synthesis powered by ChucK 더보기
Sounds Like Rain: An Immersive 3D Game-Like Audio-Visual Experience in First-Person Perspective with a Haunting Horror Ambiance Demo Video: By having my Irrational Rhythm sequencer generate the sound of rain audibly and visually generate raindrops falling towards the vertical axis, I was able to express the natural-like chaos and non-repetition through both sight and sound. Irrational Rhythm sequencer: "Each rhythm element keeps looping along its repetitive polygon pattern, but since these patterns are in the relationshi.. 더보기
Subtractive Training for Music Stem Insertion using Latent Diffusion Models https://arxiv.org/abs/2406.19328 Subtractive Training for Music Stem Insertion using Latent Diffusion ModelsWe present Subtractive Training, a simple and novel method for synthesizing individual musical instrument stems given other instruments as context. This method pairs a dataset of complete music mixes with 1) a variant of the dataset lacking a specific stemarxiv.org 더보기
Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression https://www.aes.org/e-lib/browse.cfm?elib=22266 AES E-Library » Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression AES E-Library Application of ML-Based Time Series Forecasting to Audio Dynamic Range Compression Time Series Forecasting (TSF) is used in astronomy, geology, weather forecasting, and finance to name a few. Recent research [1] has shown that, combined .. 더보기
Irrational Rhythm - for Experimental Free Jazz (live performance) Performance Video: This is an experimental free jazz performance that conveys feelings of darkness, confusion, and distress. The arrangement features piano, bass, and drums. Drum sequencer that never loops?? Instead of employing traditional rhythms based on integers or fractions, it explores the concept of playing in rhythms defined by irrational number ratios. The overall rhythm pattern, theref.. 더보기

티스토리툴바