[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[AUDITORY] Speech and Audio LM workshop at ICASSP



Dear Colleagues, 

We are proposing an ICASSP 2025 workshop: "SALMA: Speech and Audio Language Models - Architectures, Data Sources, and Training Paradigms". This workshop is a collaborative effort between UMD, CMU, Columbia, Microsoft, and will be held at ICASSP 2025 in Hyderabad, India.

This workshop aims to unite researchers specializing in various aspects of speech and audio understanding and language models, facilitating in-depth discussions and identifying synergies to develop effective methodologies aimed towards leveraging (L)LMs to enhance performance across tasks in speech, audio, and music domains, such as classification, generation, and retrieval. The workshop will half or full day (TBD) featuring four invited talks from leading figures in both industry and academia, and a poster session for accepted manuscripts. 

If you are interested to participate in this workshop, in any means, we request you to please fill up this simple form . You can find more details about the workshop, including topics of interest, here. For any questions, please do not hesitate to contact us at salmaicassp2025@xxxxxxxxx .

Best.
SALMA Organizing Committee

Sreyan Ghosh (University of Maryland College Park, MD)
Soham Deshmukh ( Microsoft and Carnegie Mellon University)
Ramani Duraiswami (University of Maryland College Park, MD)
Bhiksha Raj (Carnegie Mellon University)
Shinji Watanabe (Carnegie Mellon University)
Nima Mesgarani (Columbia University in the City of New York)
Huaming Wang (Microsoft)
Dinesh Manocha (University of Maryland College Park, MD)
P.S: Kindly pardon duplicate posts if multiple of the organizers post this.


--
Bhiksha Raj
Carnegie Mellon University
Pittsburgh, PA, USA
Tel: 412 268 9826

Attachment: SALMA_Flyer_ICASSP.pdf
Description: Adobe PDF document