A 106-hour, four-channel Mandarin egocentric speech benchmark for smart glasses with paired speaker-attributed ASR and understanding tasks finds overlap and acoustic reasoning remain the hardest problems.
SALMONN: Towards generic hearing abilities for large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models
A 106-hour, four-channel Mandarin egocentric speech benchmark for smart glasses with paired speaker-attributed ASR and understanding tasks finds overlap and acoustic reasoning remain the hardest problems.