The 1st Workshop on Speech Emotion Analysis in the Era of LLMs (SEAL) invites original and unpublished research contributions addressing the analysis, recognition, interpretation, and generation of emotion in speech. The workshop aims to bring together researchers and practitioners from computer science, engineering, artificial intelligence, linguistics, psychology, cognitive science, social science, and related disciplines to advance emotion-aware speech technologies and next-generation multimodal systems. Accepted papers will be selected through peer review and presented during the workshop alongside invited talks and technical discussions.
Topics of interest include, but are not limited to:
Tools and technologies for Speech Emotion Analysis
Speech Language Models and Speech LLMs
Generative AI and prompt engineering for Indian speech data
Agentic AI for speech-processing applications
Automatic Speech Recognition, speech synthesis, and voice conversion
Multilingual, low-resource, and code-mixed speech processing
Accent recognition, speaker verification, and dialect modeling
Disfluency identification and rectification
Music emotion analysis
Multimodal analysis involving speech, text, images, video, and memes
Healthcare and mental-health applications of emotional speech analysis
Educational and assistive speech technologies
Emotional speech corpus development, annotation, benchmarking, and evaluation
Disinformation and misinformation detection in speech
Authors are encouraged to submit high-quality theoretical, experimental, resource-oriented, or application-based research relevant to the workshop themes. Detailed submission guidelines, paper formats, important dates, registration requirements, and presentation instructions will be made available on the workshop website.
Submit your research papers using the link below: