[AUDITORY] [CfP ICASSP 2025 Workshop] Generative Data Augmentation for Real-World Signal Processing Applications (GenDA 2025)

["Kim, Minje" <minje@xxxxxxxxxxxx>]

(Apologies for cross-posting.)

Call for Papers

“Generative Data Augmentation for Real-World Signal Processing Applications”
(An ICASSP 2025 Satellite Workshop)
https://sites.google.com/view/genda2025

1. Workshop Date

TBD (a full-day workshop the day before or after the ICASSP 2025 main tracks; the details will be available when the ICASSP 2025 technical program becomes available.)  

2. Location

TBD (Sharing the same venue with ICASSP 2025 in Hyderabad, India)

3. Organizers

- Minje Kim, University of Illinois at Urbana-Champaign / Amazon Lab126  
- Dinesh Manocha, University of Maryland  
- John Hershey, Google Research  
- Trausti Kristjansson, Amazon Lab126  

4. Workshop Overview

Generative AI has revolutionized data synthesis and augmentation, offering new possibilities for signal processing. This workshop, a satellite event of ICASSP 2025, focuses on leveraging generative AI, including GANs, VAEs, Transformer-based models, and diffusion models, as well as adaptation techniques, such as zero- or few-shot learning, to create and enhance datasets for applications in speech, audio, music, and other data-sensitive multimodal signal processing domains. Participants will explore state-of-the-art AI techniques for synthesizing high-quality, diverse datasets that address data scarcity and mirror complex real-world scenarios. These datasets can be used to train models in a supervised fashion, while we also welcome contributions investigating their use in self-supervised or semi-supervised learning scenarios. The workshop will feature keynote talks, paper presentations, and panel discussions led by experts from academia and industry. Key topics include AI methodologies for realistic data generation, integrating synthetic data into workflows, and ethical considerations, including privacy-related issues, such as generative AI that can preserve the statistical properties of real data without exposing sensitive information. Technically sponsored by the Audio and Acoustics Signal Processing Technical Committee, Speech and Language Processing TC, and Data Science Initiative within IEEE SPS, this workshop is also a successor of the inaugural workshop on “Synthetic Data’s Transformative Role in Foundational Speech Models,” an Interspeech 2024 satellite workshop (https://syndata4genai.org). This workshop aims to foster a collaborative environment, inspire innovation, and push the boundaries of signal processing, AI, and data science research and practice. Join us at ICASSP 2025 to explore the transformative potential of generative AI and contribute to the future of this exciting field.

5. Topics of Interest

We invite contributions on topics including, but not limited to:

- Generative AI Techniques: Leveraging GANs, VAEs, Transformer-based models, diffusion models, autoregressive models, and other generative methods for realistic data generation.
- Data Augmentation and Enhancement: Strategies for integrating synthetic data into existing workflows to improve model performance.
- Adaptation Techniques: Approaches such as zero- or few-shot learning in the context of generative AI.
- Ethical Considerations and Privacy: Discussions on the ethical use of synthetic data, including privacy-preserving techniques.
- Application Domains: Case studies in speech, audio, music, multimedia, and cross-domain applications.
- Learning Paradigms: Exploring the use of synthetic data in supervised, self-supervised, and semi-supervised learning scenarios.

6. Submission Guidelines

We invite submissions of full papers that address the aforementioned topics. All accepted papers will be published in the IEEE Xplore Digital Library.

Important Dates:  
- Submission Deadline: November 1, 2024
- Acceptance Notification: December 18, 2024
- Camera Ready Paper Deadline: January 13, 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.)

8. Personalized Speech Enhancement Challenge

The organizers also invite submissions to the personalized speech enhancement challenge, which is designed to improve the speech denoising problem for a particular user, respecting his/her personality in the learned model. We will evaluate the speech enhancement performance of the test-time speakers, whose identity is known only by a very short utterance (~3 sec), from which the submitters are encouraged to flesh out via generative speech synthesis techniques and eventually improve their speech enhancement model. A paper on the concept and the baseline system can be found here (https://minjekim.com/wp-content/uploads/icassp2023_akuznetsova.pdf). More details will follow.

9. Workshop Format

The workshop will feature keynote presentations by leading experts, paper presentations, and panel discussions. This full-day event aims to foster collaboration, inspire innovation, and push the boundaries of signal processing research and practice.

Keynote Speakers:
- Nicholas J. Bryan (Adobe Research)
- Fabio Antonacci (Politecnico di Milano)
- Apoorv Vyas (Meta Research)

10. Contact Information

For any inquiries or additional information, please contact Minje Kim at minje@xxxxxxxxxxxx.

11. Technical Sponsors

- IEEE SPS Audio and Acoustics Signal Processing Technical Committee
- IEEE SPS Speech and Language Processing Technical Committee
- IEEE SPS Data Science Initiative