|
(Apologies for cross-posting.)
Dear list,
The organizers of the Generative Data Augmentation (GenDA) workshop at ICASSP 2025 (https://sites.google.com/view/genda2025) would like to call for contributions to the workshop for the following categories.
If you are interested in the generative AI technology and its use in data augmentation, please consider participating in the following workshop events. We hope that the workshop will serve as a platform where like-minded researchers can socialize their ideas.
1. The non-archival track paper submissions
We invite paper contributions to our non-archival track, where the authors can bring work-in-progress or already-published works. These papers won't be considered as publication as we won't send them to IEEE for publication on IEEE Xplore, but will be
posted on our website as part of the technical program. This will be a great chance to maximize your ICASSP experience if you plan to come to ICASSP anyway.
- Submission Deadline: March 1, 2025
- Acceptance Notification: March 8, 2025
- Submission URL: https://cmt3.research.microsoft.com/icassp2025/
(Choose “Satellite Workshop: Generative Data Augmentation for Real-World Signal Processing Applications” from the dropdown menu.)
(Choose "Non-Archival Track (Won't Be Published in IEEE Xplore)" as the primary subject area.)
(We will follow ICASSP 2025's paper guidelines although the papers in this track won't be published on IEEE Xplore: https://2025.ieeeicassp.org/author-kit-instructions/)
2. The room acoustics and speaker distance estimation (SDE) challenge
We welcome participation in the room acoustics and speaker distance estimation challenge. This would be a good way to evaluate your room acoustics research on this particular downstream task (SDE) or to test out different ways to improve the SDE performance.
Workshop attendance is NOT required, although we welcome presentations by the participants. More details can be found here: https://sites.google.com/view/genda2025/room
(Submission deadline: March 12, 2025)
3. Zero-shot TTS and personalized speech enhancement challenge
In this challenge, we ask participants to improve the performance of speech enhancement systems that are specially designed to work well for a target talker, whose clean speech needs to be augmented
by a zero-shot TTS system. Again, it will be a chance to showcase any TTS system's performance or to improve a speech enhancement model. Workshop attendance is NOT required, although we welcome presentations by the participants. More details can be found here: https://sites.google.com/view/genda2025/pse
(Submission deadline: March 12, 2025)
Please let the organizers know if you have any questions about these events.
Best Regards,
GenDA 2025 Organizing Committee
- Minje Kim, University of Illinois at Urbana-Champaign / Amazon Lab126
- Dinesh Manocha, University of Maryland
- John Hershey, Google Research
- Trausti Kristjansson, Amazon Lab126
- Jaesung Bae (UIUC; Task Captain of the Zero-Shot TTS and PSE Challenge)
- Jackie Lin (UIUC; Task Captain of the Room Acoustics and Speaker Distance Estimation Challenge)
|