Huan
@HuanZha80395890
Followers
458
Following
321
Media
9
Statuses
98
PhD student in AI+Music @c4dm Expressive piano performance, computational musicology, music information retrieval, music education. I play piano and theremin.
Joined February 2021
Just checked out this year's ISMIR paper list. Many interesting titles on Performance and Music Education. this year will be fun!.
1
1
11
RT @DasaemJ: 🎶Now a neural network can read scanned score image and generate performance audio in end-to-end😎.I'm super excited to introduc….
0
33
0
But we will do something quite exciting this year, stay tuned :).
0
0
0
Reading the RenCon testament back in 2003 ("The Second Rencon: Performance Contest, Panel Discussion, and the Future", Rumi Hiraga) and their future vision feels really lamenting. No, we have not get there yet 🥲
1
0
3
RT @qosmo_inc: あなたがSpotifyでヘビロテしているその楽曲、実はAI生成かも⁉️. AI生成楽曲を見破るWebツール、Spotifakeを公開しました。. SunoやUdioを使って生成した楽曲が対象です。 h….
0
273
0
Also, a little invitation! 🥁🎹.We're looking for public beta testers for this amazing app — harmono, the most engaging piano practice app I’ve played with recently, work of an independent developer, Hao Liu. This year, we’re working to see if LLaQo can be integrated into
1
0
3
🎶 Another year without in-person conference in India! . Anyways, I’m happy to take any questions on our paper LLaQo, 'presenting' on Friday at MLSP-L26 session at 3pm. We showcase the first ALM that specializes in education — an interactive music coach that's tailored to
1
0
18
Did anyone actually received the clearance letter for ICASSP….?.
1
0
3
RT @wzihanw: Why does an AI ethics expert use 'According to myself. ' at the start of their abstract in a key publication? Is it common to….
0
3
0
RT @sunjiao123sun_: Mitigating racial bias from LLMs is a lot easier than removing it from humans! . Can’t believe this happened at the bes….
0
810
0
RT @ThreatNotation: I will no longer be posting on this account. This is because Elon Musk has made this site unpleasant to use and because….
0
2K
0
#ISMIR2024. I forgot to take selfie with my posters! photo cr my amazing labmates @c4dm. Thrilled to present my two works on music performance understanding / education in my first in-person ISMIR conference 🇺🇸: . Paper: .LBD:
0
1
42
RT @c4dm: During session 4 at @ISMIRConf we presented x papers covering a wide range of MIR tasks 🎵 join us for some discussions at the pos….
0
5
0
well, let's see :).
关于中国学者是否可以去印度参加 #ICASSP2025，我向组委会询问过了（图1），得到了如下回复（图2），仅供参考（我觉得签证的办理不会像他们说的那么简单）.可以先把消息分享给朋友们，如果有后续我会及时更新。祝各位 #INTERSPEECH2024 参会愉快
0
0
0
RT @nicolaus625: 6/ 👨💻👩💻 Join us in pushing the boundaries of music and technology! [ 🎸🎼🚀.📄 For more information,….
arxiv.org
In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This comprehensive...
0
1
0
paper: repository:
github.com
Contribute to Alia-morsi/piano-synmist development by creating an account on GitHub.
0
0
5
🔥Our paper 'Simulating Piano Performance Mistakes for Music Learning' was awarded the best paper of Sound and Music Computing Conference 2024!. #SMC2024.
2
4
40
🚀 OpenWavCraft is launched!.🎉 Excited to announce that WavCraft now supports open LLMs as the backbone. WavCraft is an agent system for audio generation and editing, creating the audio content conditioned on user description and raw audio materials:
github.com
Official repo for WavCraft, an AI agent for audio creation and editing - JinhuaLiang/WavCraft
🎉 Introducing WavCraft: a breakthrough in audio editing & generation using natural language prompts! Transform sound with simple instructions & let our expert models handle the details. 🚀 Dive into our research: #AudioEditing #LanguageModeling.
2
6
15