The team behind the workshop.
Eight organizers connecting AI safety and alignment, speech and audio language models, voice privacy and human-centered AI across academia and industry in the US, Europe and Asia.
Safety, security and privacy for speech AI; ISCA SIG on Security and Privacy in Speech Communication.
Trustworthy voice agents across reliability, safety and security; LALM-as-a-Judge and MAPSS.
Audio language models and conversational AI; SALMONN and SALMONN-Guard.
Speech and language processing with less annotated data; experienced workshop and conference organizer.
Multimodal and human-centered AI; initiator of the Bidirectional Human-AI Alignment workshops.
Machine learning, NLP and multimodal agentic AI; human–AI alignment, world models and embodied agents.
Speaker and voice privacy, anonymization and speech recognition; organizer of the VoicePrivacy Challenge series.
Director of the Center for Safe Foundation Models; safe AI and causal AI.