Metraipolis › archive › dc_2d356963e415

Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models — arXiv:2610.40883

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40883
License (as archived)
CC0-1.0
Archived
2026-11-03T07:10:34.061Z
SHA-256 of the archived text
fabf82d6afad819460666932eed25d3412817f5d9c41938ec68612c8fa092185
Stable URL of this page
https://metraipolis.com/documento/dc_2d356963e415

How to cite

Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models — arXiv:2610.40883 — arXiv (en), https://arxiv.org/abs/2610.40883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d356963e415 (Metraipolis archive dc_2d356963e415, sha256 fabf82d6afad819460666932eed25d3412817f5d9c41938ec68612c8fa092185)
BibTeX
@misc{dc2d356963e415,
  title = {Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models — arXiv:2610.40883},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40883},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d356963e415; sha256 fabf82d6afad819460666932eed25d3412817f5d9c41938ec68612c8fa092185},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Voice-interactive large language models process both what a speaker says and how they say it, yet the two channels do not always agree. We ask whether that disagreement degrades speech emotion recognition. Mapping text and audio into a shared valence-arousal-dominance space, we convert the distance between them into a continuous, threshold-free incongruence score with a two-component Gaussian mixture, and validate the score against human judgement. We evaluate three audiocapable models on acted, conversational and spontaneous speech (eNTERFACE'05, MELD and CMU-MOSEI). With the model held constant across modalities, incongruence raises the odds of error whenever audio is present, in every corpus, after controlling for the ground-truth emotion and for distance in the feature space. Supervised classifiers trained on the same features behave in the opposite way, which suggests that the difficulty lies in how these models combine raw evidence rather than in the signal itself. Text-only effects are unreliable: swapping only the model that reads the transcript reverses their sign on one corpus. Rebuilding the score without the emotion lexicon reproduces the central result, and among six simpler alternatives it is the only label-free score that predicts error in all three corpora. Code, data tables and prompts are released.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.40883 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:09:31.703Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).