Junwon Lee 이준원
drawing by Joonhyung.

Junwon Lee 이준원

AI researcher
M.S. Student @ Music and Audio Computing Lab (Prof. Juhan Nam).
Research Interest: Controllable Audio Generation, Multimodal Learning, Music & Audio Information Retrieval, Machine Learning.
james39@kaist.ac.kr

News

  • Oct, 2024 | Paper on DCASE Challenge accepted to NeurIPS 2024 Audio Workshop!Link
  • Aug, 2024 | Video-Foley: preprint of my recent work on video-to-sound released!Link
  • Jun, 2024 | (DCASE) Sound Scene Synthesis Challenge Result Released!Link
  • Apr, 2024 | FAD toolkit with PANNs model Released!Link
  • Apr, 2024 | (DCASE) Sound Scene Synthesis Challenge launched! (Text-To-Audio)Link
  • Mar, 2024 | T-Foley code released!
  • | If you have any questions about joining our lab, please contact me via email :)

Publications

  • All
  • -
  • Audio
  • -
  • Music
  • -
  • Language
  • -
  • Vision
  • -
  • Generation
  • -
  • Annotation and Retrieval
Pitch-ControlNet: Continuous Pitch Control for Monophonic Instrument Sound Generation

Dabin Kim*, Junwon Lee*, Minseo Kim*, Juhan Nam

Late Breaking Demo, ISMIR 2024

#Generation #Music 

paper
Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation

Junwon Lee*, Modan Tailleur*, Laurie M. Heller*, Keunwoo Choi*, Mathieu Lagrange*, Brian McFee, Keisuke Imoto, Yuki Okamoto

Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation

#Generation #Audio 

paperopenreview
Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound

Junwon Lee, Jaekwon Im, Dabin Kim, Juhan Nam

arxiv preprint

#Generation #Audio #Vision 

paperdemocode (TBA)
CONMOD: Controllable Neural Frame-based Modulation Effects

Gyubin Lee, Hounsu Kim, Junwon Lee, Juhan Nam

Proceedings of the 27th International Conference on Digital Audio Effects (DAFx24)

#Audio 

paperdemo
Correlation of Fr ́echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant

Modan Tailleur*, Junwon Lee*, Mathieu Lagrange, Keunwoo Choi, Laurie M. Heller, Keisuke Imoto, and Yuki Okamoto (* equal contribution)

32nd European Signal Processing Conference (EUSIPCO), 2024

#Generation #Audio 

paperfadtk (FAD toolkit)
T-FOLEY: A Controllable Waveform-Domain Diffusion Model For Temporal-Event-Guided Foley Sound Synthesis

Yoonjin Chung*, Junwon Lee*, and Juhan Nam (* equal contribution)

Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

#Generation #Audio 

paperdemocode
Foley Sound Synthesis In Waveform Domain With Diffusion Model

Yoonjin Chung, Junwon Lee, and Juhan Nam

DCASE 2023 Challenge Task 7 Foley Sound Synthesis Technical Report (15th, 1st model w/o phase reconstruction model)

#Generation #Audio 

paper
Music Playlist Title Generation Using Artist Information

Haven Kim, Seungheon Doh, Junwon Lee, and Juhan Nam

AAAI-23 Workshop on Creative AI Across Modalities

#Generation #Language #Music 

paper
Music Playlist Title Generation: A Machine-Translation Approach

Seungheon Doh, Junwon Lee, and Juhan Nam

2nd Workshop on Natural Language Processing for Music and Spoken Audio (NLP4MusA), 2021

#Generation #Language #Music 

paper