Saved in:
Bibliographic Details
Main Authors: Chua, ChenYi, Wong, JunKai, Chen, Chengxin, Miao, Xiaoxiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.20796
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916923581661184
author Chua, ChenYi
Wong, JunKai
Chen, Chengxin
Miao, Xiaoxiao
author_facet Chua, ChenYi
Wong, JunKai
Chen, Chengxin
Miao, Xiaoxiao
contents In this paper, we propose a multimodal framework for speech emotion recognition that leverages entropy-aware score selection to combine speech and textual predictions. The proposed method integrates a primary pipeline that consists of an acoustic model based on wav2vec2.0 and a secondary pipeline that consists of a sentiment analysis model using RoBERTa-XLM, with transcriptions generated via Whisper-large-v3. We propose a late score fusion approach based on entropy and varentropy thresholds to overcome the confidence constraints of primary pipeline predictions. A sentiment mapping strategy translates three sentiment categories into four target emotion classes, enabling coherent integration of multimodal predictions. The results on the IEMOCAP and MSP-IMPROV datasets show that the proposed method offers a practical and reliable enhancement over traditional single-modality systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20796
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speech Emotion Recognition via Entropy-Aware Score Selection
Chua, ChenYi
Wong, JunKai
Chen, Chengxin
Miao, Xiaoxiao
Sound
Artificial Intelligence
In this paper, we propose a multimodal framework for speech emotion recognition that leverages entropy-aware score selection to combine speech and textual predictions. The proposed method integrates a primary pipeline that consists of an acoustic model based on wav2vec2.0 and a secondary pipeline that consists of a sentiment analysis model using RoBERTa-XLM, with transcriptions generated via Whisper-large-v3. We propose a late score fusion approach based on entropy and varentropy thresholds to overcome the confidence constraints of primary pipeline predictions. A sentiment mapping strategy translates three sentiment categories into four target emotion classes, enabling coherent integration of multimodal predictions. The results on the IEMOCAP and MSP-IMPROV datasets show that the proposed method offers a practical and reliable enhancement over traditional single-modality systems.
title Speech Emotion Recognition via Entropy-Aware Score Selection
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2508.20796