Yi-Hsuan Yang
@affige_yang
Followers
2K
Following
4K
Statuses
792
1 Professor, EE, National Taiwan University 2 Chief Music Scientist, Taiwan AI Labs
Taipei, Taiwan
Joined July 2013
🔊Teaching a new graduate-level course on "Deep Learning for Music Analysis and Generation" at National Taiwan University. I'll be sharing the slides at the link below (feedbacks are welcome; please DM me) -
3
56
286
RT @keunwoochoi: @AIatMeta open sourced a new model for audio quality evaluation. imo it makes a lot of sense sinc…
0
5
0
RT @deeplearnmusic: 🧑🎓Our @ISMIRConf Tutorial "Deep Learning 101 for Audio-based MIR" provides a broad introduction to music audio proces…
0
13
0
RT @Or__Tal: Release Announcement!📢💣 🥁🎷JASCO 🎶🪇 training & inference code + model weights are out! Paper📜: Sample…
0
21
0
RT @ArxivSound: ``Guitar-TECHS: An Electric Guitar Dataset Covering Techniques, Musical Excerpts, Chords and Scales Using a Diverse Array o…
0
6
0
RT @yukara_ikemiya: 🎼 Minimal MusicGen for developers MusicGen is a simple and high-quality music generative model, but its official reposi…
0
13
0
RT @bhandari10k: 🎉 Excited to announce that our paper "Text2MIDI: Generating Symbolic Music from Captions" has been accepted at #AAAI2025!…
0
2
0
RT @Chen_Paul_u: 🚀 Introducing AI TrackMate at @NeurIPSConf 2024 Creative AI Track! 🚀 🎧 Drop in your audio, AI TrackMate listen, chat, an…
0
14
0
RT @YuHuaChen12: We are happy to announce that the short version of our zero-shot amplifier modeling paper has been accepted to the #ismir2…
0
9
0
RT @fundwotsai2001: We released the SDEdit code for AudioLDM2 used in Audio Prompt Adapter: Welcome to use it and…
0
2
0
RT @mhnt1580: As a speech/audio researcher, I think it’s a big breakthrough in advancing *human-level audio generation*. Why? Because th…
0
8
0
RT @NicholasJBryan: Ultra fast music generation via accelerating diffusion TTM without quality loss. Amazing work led by @zacknovack! Sum…
0
8
0
RT @JLenzyy: 🎵🪇 Expressive Generation and Variations on Symbolic Music 🎶🎻 So excited to announce that the first 🍋@lemonaidexmusic research…
0
17
0
RT @shaohua0116: Thrilled to share that four papers I co-authored have been accepted to #NeurIPS2024, and the topics span reinforcement lea…
0
8
0
RT @ArxivSound: ``FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs,'' Hitoshi Suda, Shunsuke Yoshida, Tomohiko Nakamura, Sator…
0
7
0
METEOR is a multitrack MuseMorphose extension that offers bar- & track-level texture control for orchestral music style transfer, re-instrumentation and leadsheet orchestration; done by a visiting student Viet-Toan from Univ. Lille.
0
6
23
RT @_akhaliq: Seed-Music A Unified Framework for High Quality and Controlled Music Generation discuss: We introd…
0
90
0
RT @sai_soum_: Yesterday @marcoamaram and I presented a hands-on tutorial on AI for Multitrack Mixing at @dafx2024 at the @UniOfSurrey. Fin…
0
12
0
RT @sedielem: Diffusion is the rising tide that eventually submerges all frequencies, high and low 🌊 Diffusion is the gradual decompositio…
0
165
0