Jongmin `sake` Jung

Deep Learning, Music Information Retrieval Researcher

[Jongmin `sake` Jung @sake_min]

Excited to share that our paper "U-MusT" is now published in IEEE TASLPRO.
Big thanks to @DasaemJ, @dmkim_omrguy, @is_s_yun, Seola Cho, Irmak Bukey, Hyungjoon Soh, and @chrisdonahuey!

https://t.co/575w898nn5

[Dasaem Jeong @DasaemJ]

🎶Now a neural network can read scanned score image and generate performance audio in end-to-end😎
I'm super excited to introduce our work on Unified Cross-modal translation between Score Image, Symbolic Music, and Audio.
Why does it matter and how to make it? Check the thread🧵

[Jongmin `sake` Jung @sake_min]

Had a fantastic time at #ICASSP2026 in Barcelona presenting our IEEE TASLP paper, U-MusT! 🇪🇸🎵
A big thank you to everyone who stopped by our poster session for the great discussions and insights!

📄 Paper: https://t.co/575w898nn5

[Sihun Lee @is_s_yun]

Breathing #ICASSP air with @sake_min and @dmkim_omrguy

[Jongmin `sake` Jung @sake_min]

@junmingong Hi, I saw DCW implementation commits on ACE-Step 1.5 repo. Do you find it solves the fidelity problem?

[Jongmin `sake` Jung @sake_min]

@DasaemJ @dmkim_omrguy @is_s_yun @chrisdonahuey The paper will be presented in @ieeeICASSP 2026 in Barcelona. Looking forward to valuable discussions!

[Jongmin `sake` Jung @sake_min]

Excited to share that our paper "U-MusT" is now published in IEEE TASLPRO.
Big thanks to @DasaemJ, @dmkim_omrguy, @is_s_yun, Seola Cho, Irmak Bukey, Hyungjoon Soh, and @chrisdonahuey!

https://t.co/575w898nn5

[Dasaem Jeong @DasaemJ]

🎶Now a neural network can read scanned score image and generate performance audio in end-to-end😎
I'm super excited to introduce our work on Unified Cross-modal translation between Score Image, Symbolic Music, and Audio.
Why does it matter and how to make it? Check the thread🧵

[Jongmin `sake` Jung @sake_min]

Tired of switching windows just to check a MIDI file while coding in VS Code?
Now you can open and play MIDI files on VS Code with this extension, WaveRoll Studio!

[초승달/Hannah Park🌙 @crescent_stdio]

Ever opened a MIDI file in an IDE and got this?
"The file is not displayed in the text editor because it is either binary or uses an unsupported text encoding."

I built an extension to solve it: WaveRoll Studio!

VS Code: https://t.co/aU7Gh1lEht
Open VSX: https://t.co/cXn70K5kFG

[Jongmin `sake` Jung @sake_min]

Still buzzing from #ISMIR2025!

🎤 Honored to present our U-MusT work at #LLM4MA & demo its extension Contin-U at #RenCon.

🏢 So proud of the warm reception for my company, @mixaudio_ by Neutune!

🎉 Loved being Social Media Chair & our K-Culture Night was a massive success!

[Jongmin `sake` Jung @sake_min]

Waiting for you to come and meet at Daejeon, Korea!
See you all soon @ISMIRConf 2025!

[ISMIR Conference @ISMIRConf]

📅 ISMIR 2025 Full Schedule is Live! 📅

Plan your week in Daejeon, Korea with the full program of talks, tutorials, concerts, and special events.

From inspiring keynotes to the BARAJI Korean Traditional Music Concert, and from industry meetups to the legendary banquet & jam session 🎶

👉 Explore the full schedule here: https://t.co/8adxzFHkzg

🗓️ Tip: You can also download the .ics file from the program page and add all sessions directly to your personal calendar!

Get ready for an amazing week of music, research, and community at ISMIR 2025 💜

[Huan @HuanZha80395890]

We are excited to announce that the online audition phase for RenCon 2025 has officially begun!

RenCon 2025 is an international challenge where researchers and developers submit systems capable of rendering expressive musical performances from symbolic scores.
We need your help as judges for the preliminary round! The online evaluation allows the community to listen to and rate the submitted performances, helping us select the top systems for the live contest at ISMIR.

Evaluation page: https://t.co/C6s2OG3hcB
Submissions: Each participant has submitted 2 required pieces and 1 free-choice piece, and we have anonymized them.
Rating entry: Provide your assessment in google form: https://t.co/ZQIf9BwZXC
Deadline for evaluation: September 15, 2025 (AoE)

Your expertise and participation are crucial for the success of this competition. The top systems from this online phase will advance to the live contest at ISMIR 2025 in Daejeon, Korea.
For more information about RenCon 2025, please visit: https://t.co/CLNudMTZyg

[Jongmin `sake` Jung @sake_min]

https://t.co/k5cbBXZ8Yt

[Jongmin `sake` Jung @sake_min]

Amazing

[ISMIR Conference @ISMIRConf]

🎤 #ISMIR2025 Keynote Announcement 1️⃣

We are delighted to welcome Soo-man Lee (Key Producer & Visionary Leader, A2O Entertainment) as a keynote speaker! 🌍🎶

📌 Talk title: Culture Technology in the Age of AI
Soo-man Lee, founder of SM Entertainment and A2O Entertainment, who pioneered the concept of "Culture Technology (CT)," will share his vision on how culture and technology converge to drive the global growth of K-Pop. His keynote explores how CT—spanning artist training, content creation, and technology integration—can catalyze a future where fans become creators and AI accelerates human creativity.

Join us as we explore how CT will shape the next frontier of music, culture, and technology.

🔗 More details: https://t.co/zf6bY9Np1o

#MusicAI #MIR #Kpop #Keynote #CultureTech

[arXiv Sound @ArxivSound]

Yonghyun Kim, Wayne Chi, Anastasios N. Angelopoulos, Wei-Lin Chiang, Koichi Saito, Shinji Watanabe, Yuki Mitsufuji, Chris Donahue, "Music Arena: Live Evaluation for Text-to-Music," https://t.co/78N4ruLzKz

[Jongmin `sake` Jung @sake_min]

@rvm0n_ Here it is :)

12 Etudes, Op.8 – Alexander Scriabin Alexander Scriabin: Etude in F# Minor, Op.8 No.2

https://t.co/mkgRMEUFOf

[Jongmin `sake` Jung @sake_min]

Generating continuous performance audio directly from full score images 🎼→🎧

I've been working on generating performance audio from full score images, with the model from my latest research, U-MusT.

Check below and see how I implemented this!

[Dasaem Jeong @DasaemJ]

🎶Now a neural network can read scanned score image and generate performance audio in end-to-end😎
I'm super excited to introduce our work on Unified Cross-modal translation between Score Image, Symbolic Music, and Audio.
Why does it matter and how to make it? Check the thread🧵

[Jongmin `sake` Jung @sake_min]

Input Score: Pokemon Centre (Day) - Pokémon Diamond/Pearl/Platinum by OliverKmusic

https://t.co/mIIiREnwuI

[Jongmin `sake` Jung @sake_min]

Unified Cross-modal translation between Score Image, Symbolic Music, and Audio

arXiv: https://t.co/KojkzgKtRY
demo: https://t.co/IX5Kc2ldhn

[Hao-Wen (Herman) Dong 董皓文 @hermanhwdong]

🔥Happy to announce that the AI for Music Workshop is coming to #NeurIPS2025!

We have an amazing lineup of speakers! We call for papers & demos (due on August 22)!

See you in San Diego!🏖️

@chrisdonahuey @Ilaria__Manco @zawazaw @huangcza @McAuleyLabUCSD @zacknovack @NeurIPSConf