一作ACL 2026Findings· Findings of ACL
WESR : A Benchmark and Strong Baseline for Word-level Event-Speech Recognition
Chenchen Yang · Kexin Huang · Liwei Fan · Qian Tu · Botian Jiang · Dong Zhang · Linqi Yin · Shimin Li · Zhaoye Fei · Qinyuan Cheng · Xipeng Qiu
摘要
Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localization of non-verbal events remains a critical yet under-explored challenge. Current methods suffer from insufficient t...