AI BriefingInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2026
Key point
Apple will present three new research papers at ICASSP 2026 in Barcelona from May 4-8.
Details
Apple is participating in ICASSP 2026, showcasing research at booth #P2 at CCIB in Barcelona, Spain. The exhibition runs May 4, 19:00-21:30, and May 5-8, 09:00-17:00 (CEST), and Apple is also participating as a sponsor.
A total of 3 papers will be presented.
- Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models: May 6, 16:30-18:30, SLP-P25, Poster Area 27
- StereoFoley: Object-Aware Stereo Audio Generation from Video: May 8, 14:00-16:00, AASP-P30, Poster Area 25
- Principled Coarse-Grained Acceptance for Speculative Decoding in Speech: May 8, 15:00-15:20, SLP-L20, Room 114
The three papers cover audio-visual learning, video-based stereo audio generation, and improving the efficiency of speculative decoding for speech. Co-authors also include researchers from Tampere University, UC San Diego, and Tel Aviv University.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Apple Releases LensVLM-9B for Processing Compressed Text Images