-
Music and Audio Research Group, Seoul National University
- Seoul, Republic of Korea
- linkedin.com/in/junghyun-koo-525a31251
- @Junghyun_Koo
- https://scholar.google.com/citations?user=9LbxECcAAAAJ&hl=en
- https://www.semanticscholar.org/author/Junghyun-Koo/151486141
Stars
code for "BEAT-ALIGNED SPECTROGRAM-TO-SEQUENCE GENERATION OF RHYTHM-GAME CHARTS" (ISMIR 2023 LBD)
code for "DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper"
ldzhangyx / simplified-jukemir
Forked from p-lambda/jukemirA minimum JukeMIR branch for feature extraction.
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
FxNorm-Automix - Implementation of automatic music mixing systems. We show how we can use wet music data and repurpose it to train a fully automatic mixing system
Evaluation kit for the HEAR Benchmark
Collection of audio-focused loss functions in PyTorch
Steerable discovery of neural audio effects
Third-party audio effects plugins as differentiable layers within deep neural networks.
Headless multitrack mixing console in Python
Official PyTorch implementation of Contrastive Learning of Musical Representations