I was recognized as "Ajou Honorary Alumni" along with my then-gf-now-wife, Kahyun Choi, by our alma mater, Ajou University. While I'm deeply humbled, it's so cute that they paired us together as a team. Also, the Ghibli-style image! The cutest plaque I've ever received!

🎉 Our new paper, accepted to #ISMIR2025, presents "GuideSep," an interactive music source separation system guided by users (e.g., humming or sketching on a spectrogram). Built on GenAI, it achieves clean separation! Demo: yutongwen.github.io/GuideSep/ Paper: minjekim.com/wp-content/u...

Please plan to come to my virtual talk at the conversational AI reading @convai-rg.bsky.social led by @poonehm.bsky.social! More information👇

View of the Granlibakken Tahoe resort and Lake Tahoe

It’s official! 🎉
WASPAA 2025 will be held October 12-15 at the Granlibakken Tahoe resort, in Tahoe City, CA🏞️
Important dates:
Abstract deadline: April 23, 2025 (23:59 AOE)
Paper deadline: April 30, 2025 (23:59 AOE)
Acceptance: July 2, 2025
Camera-ready: July 16, 2025
More info: waspaa.com
Please RT🤗

Many thanks to my co-author Jan Skoglund and the editors of the special issue, Sharon Gannot, Walter Kellermann, Zbyněk Koldovský, Shoko Araki, and Gaël Richard!

Neural Speech and Audio Coding: Modern AI technology meets traditional codecs This article explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluat...

Our review paper, “Neural Speech and Audio Coding,” has been published in IEEE SPM. This focused review paper introduces harmonization of traditional coding methods modern AI-based approaches:
IEEE Xplore: ieeexplore.ieee.org/document/108...
Authors’ version: arxiv.org/abs/2408.06954

Note that we will follow ICASSP 2025's paper guidelines: 2025.ieeeicassp.org/author-kit-i...

(Choose “Satellite Workshop: Generative Data Augmentation for Real-World Signal Processing Applications” from the dropdown menu. Then, choose "Non-Archival Track (Won't Be Published in IEEE Xplore)" as the primary subject area.)

- Submission Deadline: March 1, 2025
- Acceptance Notification: March 8, 2025
- Workshop Date: April 7, 2025 (Full Day)
- Submission URL: cmt3.research.microsoft.com/icassp2025/

These papers won't be published on IEEE Xplore, but will be posted on our website as part of the workshop's technical program. Authors are also invited to present at the workshop—just another fun event to participate in at
@ieeeICASSP.

📣 Non-archival track paper submissions for the Generative Data Augmentation (#GenDA2025) workshop are still welcome! Deadline March 1st. 📣
Work-in-progress or already-published works are welcome. CfP drive.google.com/file/d/1P6oQ...
@ieeeICASSP

The deadline is by March 12. Participants are welcome to present their work at our GenDA workshop at ICASSP 2025. More information on the workshop: sites.google.com/view/genda20... Let me know if you have any questions, and please spread the word!

We provide all source codes and baseline implementations of the downstream tasks (PSE and SDE), so you don't have to develop any of them from scratch. Instead, this must be a fun way to show off your generative models' usefulness for other downstream tasks!

GenDA 2025 - Room Acoustics and Speaker Distance Estimation Challenge Introduction This challenge calls for RIR generation systems to augment RIR data for the downstream task, speaker distance estimation (SDE), as part of the Generative Data Augmentation workshop at ICA...

🎈 Room acoustics and speaker distance estimation: Augment the room impulse response data of a target room to improve the (single-channel) speaker distance estimation task. More details: sites.google.com/view/genda20...

GenDA 2025 - Zero-Shot TTS and PSE Challenge Introduction This challenge calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as part of the Generative Data Augme...

🎈 Zero-shot TTS and personalized speech enhancement: Augment a target speaker's speech using your zero-shot TTS model and show it improves a speaker-specific speech enhancement task. More details: sites.google.com/view/genda20...

📣 📣 TWO challenges at the Generative Data Augmentation (GenDA) workshop at ICASSP 2025! 📣 📣
#ICASSP2025

2024 was a heartwarming year with many changes in my life. Probably one of the most fun things was to meet new students and to teach them in the good old Siebel Center. Picture is from the last day of the fall semester (posting with students’ permission). Looking forward to the year of 2025!

WASPAA is moving, for the first time in its almost 40-year history. Stay tuned for the announcement of the new venue!

@waspaa.com is on Bluesky!
Big changes are coming for WASPAA 2025!

Me me me!