Unified Audio Schema adds structured paralinguistic and event labels to audio training data, raising fine-grained perception scores by 10.9% on MMSU while keeping reasoning intact.
In2023 IEEE Automatic Speech Recog- nition and Understanding Workshop (ASRU), pages 1–8
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs
Unified Audio Schema adds structured paralinguistic and event labels to audio training data, raising fine-grained perception scores by 10.9% on MMSU while keeping reasoning intact.