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

arXiv: https://arxiv.org/abs/2609.16582 · HTML: https://mlsanity.com/paper/2609.16582/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!](https://mlsanity.com/paper/2010.06572/) (2020)
- [Voxtral](https://mlsanity.com/paper/2507.13264/) (2025)
- [Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance](https://mlsanity.com/paper/2510.10444/) (2025)
- [Probing Speech Emotion Recognition Transformers for Linguistic Knowledge](https://mlsanity.com/paper/2204.00400/) (2022)
- [A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm](https://mlsanity.com/paper/2408.14892/) (2024)
- [Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects](https://mlsanity.com/paper/2509.04605/) (2025)
- [Modeling Sarcastic Speech: Semantic and Prosodic Cues in a Speech Synthesis Framework](https://mlsanity.com/paper/2510.07096/) (2025)
- [CHARM: Charge Calibration and Acoustic Rescue for LLM-based Multimodal Sarcasm Detection](https://mlsanity.com/paper/2607.11102/) (2026)
- [When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection](https://mlsanity.com/paper/2608.30204/) (2026)

## Built on by (most cited first, 1 of 1)

- [Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change](https://mlsanity.com/paper/2609.35922/) (2026)

## Abstract (arXiv)

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.