CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection

2026-09-14

AI Summary

研究通过CLASH框架评估语音讽刺检测中词汇和韵律线索的作用，发现词汇保留的语音在检测中比韵律保留的更有效。

Abstract

Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under original, lexical-preserving, prosody-preserving, and approximately neutralised conditions. We evaluate handcrafted acoustic-feature systems, self-supervised learning (SSL) probes, and large audio language models (LALMs) on CMMA and MUStARD. For target-only Qwen3-Omni, lexical-preserving speech retains a 0.135--0.148 AUROC advantage over prosody-preserving speech after duration balancing, with cluster-bootstrap intervals above zero; alternative lexical resynthesis preserves this advantage. Acoustic interventions shift scores without consistently improving discrimination or changing binary predictions under the evaluated conditions. Context and interaction estimates vary across corpora. These findings distinguish acoustic sensitivity from sarcasm discrimination while exposing duration, identity, and transformation effects.

Problem

• spoken sarcasm detection
• lexical content
• prosody
• conventional evaluation

Innovation

• CLASH
• counterfactual diagnostic framework
• spoken sarcasm detection
• lexical-preserving
• prosody-preserving