task · first seen 12 Oct 2026
audio-visual speech recognition
Speech recognition that uses visual context from video or screens alongside audio to improve transcription.
Mentions per week
PapersCodeDiscussion
Earliest sources
- ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual ContextPapers · 12 Oct 2026 · Mingwei Fu, Zheshu Song, Zhikai Zhou, Shen Huang, Shidong Shang, Mengxiao Zhu
Latest sources
- ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual ContextPapers · 12 Oct 2026 · Mingwei Fu, Zheshu Song, Zhikai Zhou, Shen Huang, Shidong Shang, Mengxiao Zhu