Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Rongchen, Francoeur, Vincent, Nejadgholi, Isar, Gagnon, Sylvain, Bolic, Miodrag
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.03060
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914072660803584
author Guo, Rongchen
Francoeur, Vincent
Nejadgholi, Isar
Gagnon, Sylvain
Bolic, Miodrag
author_facet Guo, Rongchen
Francoeur, Vincent
Nejadgholi, Isar
Gagnon, Sylvain
Bolic, Miodrag
contents Speech Emotion Recognition (SER) is essential for improving human-computer interaction, yet its accuracy remains constrained by the complexity of emotional nuances in speech. In this study, we distinguish between descriptive semantics, which represents the contextual content of speech, and expressive semantics, which reflects the speaker's emotional state. After watching emotionally charged movie segments, we recorded audio clips of participants describing their experiences, along with the intended emotion tags for each clip, participants' self-rated emotional responses, and their valence/arousal scores. Through experiments, we show that descriptive semantics align with intended emotions, while expressive semantics correlate with evoked emotions. Our findings inform SER applications in human-AI interaction and pave the way for more context-aware AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03060
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic Differentiation in Speech Emotion Recognition: Insights from Descriptive and Expressive Speech Roles
Guo, Rongchen
Francoeur, Vincent
Nejadgholi, Isar
Gagnon, Sylvain
Bolic, Miodrag
Computation and Language
Artificial Intelligence
Speech Emotion Recognition (SER) is essential for improving human-computer interaction, yet its accuracy remains constrained by the complexity of emotional nuances in speech. In this study, we distinguish between descriptive semantics, which represents the contextual content of speech, and expressive semantics, which reflects the speaker's emotional state. After watching emotionally charged movie segments, we recorded audio clips of participants describing their experiences, along with the intended emotion tags for each clip, participants' self-rated emotional responses, and their valence/arousal scores. Through experiments, we show that descriptive semantics align with intended emotions, while expressive semantics correlate with evoked emotions. Our findings inform SER applications in human-AI interaction and pave the way for more context-aware AI systems.
title Semantic Differentiation in Speech Emotion Recognition: Insights from Descriptive and Expressive Speech Roles
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.03060