Metraipolis › archive › dc_eadf0f2db71f
Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition — arXiv:2609.05755
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05755
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:49:49.306Z
- SHA-256 of the archived text
e8ce95ad66253085a34b7ac76e99df705f6e2163f50a34712bd1820f77b573f8- Stable URL of this page
https://metraipolis.com/documento/dc_eadf0f2db71f
How to cite
Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition — arXiv:2609.05755 — arXiv (en), https://arxiv.org/abs/2609.05755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eadf0f2db71f (Metraipolis archive dc_eadf0f2db71f, sha256 e8ce95ad66253085a34b7ac76e99df705f6e2163f50a34712bd1820f77b573f8)
BibTeX
@misc{dceadf0f2db71f,
title = {Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition — arXiv:2609.05755},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05755},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eadf0f2db71f; sha256 e8ce95ad66253085a34b7ac76e99df705f6e2163f50a34712bd1820f77b573f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human emotion is graded and frequently mixed, yet most multimodal recognizers collapse it onto a single hard label. We argue the recognizer should instead expose a distribution over affective space. Our text+speech system, alongside its categorical decision, emits a $9\times9$ probability matrix over the Valence-Arousal plane, trained with a two-dimensional Gaussian soft target under a Kullback-Leibler/cross-entropy objective, aimed at counseling support. Evaluation is strict: speaker-independent 5-fold leave-one-session-out IEMOCAP with rotating-session inner validation, headline metrics only on the held-out session. Within one fixed encoder-fusion-head pipeline we compare Transformer and state-space (Mamba-1/2/3) backbones at matched depth and width, at two operating points ($T\approx550$, $T\approx2750$). The featured dual-head system reaches 73.0% $\pm$ 0.3 unweighted accuracy over three seeds (separate rerun: 72.1%), exceeding the Transformer fusion baseline by 3.0 UA points (95% session-bootstrap CI [1.0,4.7]; significant under paired t-test and session-level bootstrap), with no latency or memory advantage at these lengths; swapping the ~1M trainable front-end for frozen WavLM-Large features (learnable layer weights) lifts the same architecture to 76.6% $\pm$ 1.3. Pre-specified controls scope the claims honestly: simpler valence-arousal auxiliaries reproduce the classification lift within noise, and a dedicated regression head tracks the continuous ratings slightly better, so the head's specific value is the normalized affect distribution itself. That distribution recovers the circumplex: its center of mass tracks valence and arousal (CCC 0.66/0.66; predominantly between-class structure, weaker within-class tracking), and its entropy is weakly but consistently linked to categorical rater ambiguity, not dimensional spread. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.05755 — 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 2026-10-16T12:30:25.236Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).