Metraipolis › archive › dc_44960b73396f

Robust Speech Emotion Recognition under Tone-Word Conflict: A Benchmark and Framework — arXiv:2609.04236

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04236
License (as archived)
CC0-1.0
Archived
2026-10-17T00:43:25.446Z
SHA-256 of the archived text
facacc1d0061547bdfb04e3a3a794faa4e7d9c63e85e4c1802969782b96146b9
Stable URL of this page
https://metraipolis.com/documento/dc_44960b73396f

How to cite

Robust Speech Emotion Recognition under Tone-Word Conflict: A Benchmark and Framework — arXiv:2609.04236 — arXiv (en), https://arxiv.org/abs/2609.04236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44960b73396f (Metraipolis archive dc_44960b73396f, sha256 facacc1d0061547bdfb04e3a3a794faa4e7d9c63e85e4c1802969782b96146b9)
BibTeX
@misc{dc44960b73396f,
  title = {Robust Speech Emotion Recognition under Tone-Word Conflict: A Benchmark and Framework — arXiv:2609.04236},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04236},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44960b73396f; sha256 facacc1d0061547bdfb04e3a3a794faa4e7d9c63e85e4c1802969782b96146b9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech emotion recognition (SER) is a crucial component of human-computer interaction, attracting extensive attention from both industry and academia. However, existing SER systems typically assume alignment between vocal tone and lexical semantics, overlooking the real-world scenarios that involve tone-word conflict-where the emotion conveyed by speech contradicts the literal meaning of the words. To bridge this gap, we introduce TWIN-SER (Tone-Word Incongruent SER), a benchmark for systematic evaluation under acoustic-semantic incongruence, and show that state-of-the-art models degrade severely under such incongruence. To address this, we propose DAS (Disentangled Acoustic-Semantic fusion), a framework that mitigates tone-word conflict by explicitly disentangling acoustic and semantic pathways, selecting informative high-energy embeddings, and adaptively fusing them via a lightweight query-based attention mechanism. Specifically, DAS comprises three crucial modules: i) a heterogeneous feature extraction module that separately captures complementary acoustic and semantic representations from raw input; ii) a high-energy embedding selection module that identifies and retains the most discriminative embeddings; and iii) a Q-Former combination module that bridges the two pathways through cross-attention, enabling robust emotion prediction under incongruent conditions. Extensive experiments demonstrate that DAS consistently outperforms existing methods in tone-word conflict scenarios, as well as in standard in-domain and zero-shot settings. Our code and datasets are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.04236 — 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 2026-10-17T00:21:40.218Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).