Saved in:
Bibliographic Details
Main Authors: Wu, Jingyao, Lin, Grace, Song, Yinuo, Picard, Rosalind
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914280115273728
author Wu, Jingyao
Lin, Grace
Song, Yinuo
Picard, Rosalind
author_facet Wu, Jingyao
Lin, Grace
Song, Yinuo
Picard, Rosalind
contents Emotion recognition is inherently ambiguous, with uncertainty arising both from rater disagreement and from discrepancies across modalities such as speech and text. There is growing interest in modeling rater ambiguity using label distributions. However, modality ambiguity remains underexplored, and multimodal approaches often rely on simple feature fusion without explicitly addressing conflicts between modalities. In this work, we propose AmbER$^2$, a dual ambiguity-aware framework that simultaneously models rater-level and modality-level ambiguity through a teacher-student architecture with a distribution-wise training objective. Evaluations on IEMOCAP and MSP-Podcast show that AmbER$^2$ consistently improves distributional fidelity over conventional cross-entropy baselines and achieves performance competitive with, or superior to, recent state-of-the-art systems. For example, on IEMOCAP, AmbER$^2$ achieves relative improvements of 20.3% on Bhattacharyya coefficient (0.83 vs. 0.69), 13.6% on R$^2$ (0.67 vs. 0.59), 3.8% on accuracy (0.683 vs. 0.658), and 4.5% on F1 (0.675 vs. 0.646). Further analysis across ambiguity levels shows that explicitly modeling ambiguity is particularly beneficial for highly uncertain samples. These findings highlight the importance of jointly addressing rater and modality ambiguity when building robust emotion recognition systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18010
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AmbER$^2$: Dual Ambiguity-Aware Emotion Recognition Applied to Speech and Text
Wu, Jingyao
Lin, Grace
Song, Yinuo
Picard, Rosalind
Audio and Speech Processing
Sound
Emotion recognition is inherently ambiguous, with uncertainty arising both from rater disagreement and from discrepancies across modalities such as speech and text. There is growing interest in modeling rater ambiguity using label distributions. However, modality ambiguity remains underexplored, and multimodal approaches often rely on simple feature fusion without explicitly addressing conflicts between modalities. In this work, we propose AmbER$^2$, a dual ambiguity-aware framework that simultaneously models rater-level and modality-level ambiguity through a teacher-student architecture with a distribution-wise training objective. Evaluations on IEMOCAP and MSP-Podcast show that AmbER$^2$ consistently improves distributional fidelity over conventional cross-entropy baselines and achieves performance competitive with, or superior to, recent state-of-the-art systems. For example, on IEMOCAP, AmbER$^2$ achieves relative improvements of 20.3% on Bhattacharyya coefficient (0.83 vs. 0.69), 13.6% on R$^2$ (0.67 vs. 0.59), 3.8% on accuracy (0.683 vs. 0.658), and 4.5% on F1 (0.675 vs. 0.646). Further analysis across ambiguity levels shows that explicitly modeling ambiguity is particularly beneficial for highly uncertain samples. These findings highlight the importance of jointly addressing rater and modality ambiguity when building robust emotion recognition systems.
title AmbER$^2$: Dual Ambiguity-Aware Emotion Recognition Applied to Speech and Text
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2601.18010