EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jingwen, Cheng, Kan Jen, Lian, Jiachen, Anand, Akshay, Jain, Rishi, Qiao, Faith, Netzorg, Robin, Chou, Huang-Cheng, Li, Tingle, Lin, Guan-Ting, Anumanchipalli, Gopala
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914005162917888
author Liu, Jingwen
Cheng, Kan Jen
Lian, Jiachen
Anand, Akshay
Jain, Rishi
Qiao, Faith
Netzorg, Robin
Chou, Huang-Cheng
Li, Tingle
Lin, Guan-Ting
Anumanchipalli, Gopala
author_facet Liu, Jingwen
Cheng, Kan Jen
Lian, Jiachen
Anand, Akshay
Jain, Rishi
Qiao, Faith
Netzorg, Robin
Chou, Huang-Cheng
Li, Tingle
Lin, Guan-Ting
Anumanchipalli, Gopala
contents Speech emotions play a crucial role in human-computer interaction, shaping engagement and context-aware communication. Despite recent advances in spoken dialogue systems, a holistic system for evaluating emotional reasoning is still lacking. To address this, we introduce EMO-Reasoning, a benchmark for assessing emotional coherence in dialogue systems. It leverages a curated dataset generated via text-to-speech to simulate diverse emotional states, overcoming the scarcity of emotional speech data. We further propose the Cross-turn Emotion Reasoning Score to assess the emotion transitions in multi-turn dialogues. Evaluating seven dialogue systems through continuous, categorical, and perceptual metrics, we show that our framework effectively detects emotional inconsistencies, providing insights for improving current dialogue systems. By releasing a systematic evaluation benchmark, we aim to advance emotion-aware spoken dialogue modeling toward more natural and adaptive interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems
Liu, Jingwen
Cheng, Kan Jen
Lian, Jiachen
Anand, Akshay
Jain, Rishi
Qiao, Faith
Netzorg, Robin
Chou, Huang-Cheng
Li, Tingle
Lin, Guan-Ting
Anumanchipalli, Gopala
Computation and Language
Audio and Speech Processing
Speech emotions play a crucial role in human-computer interaction, shaping engagement and context-aware communication. Despite recent advances in spoken dialogue systems, a holistic system for evaluating emotional reasoning is still lacking. To address this, we introduce EMO-Reasoning, a benchmark for assessing emotional coherence in dialogue systems. It leverages a curated dataset generated via text-to-speech to simulate diverse emotional states, overcoming the scarcity of emotional speech data. We further propose the Cross-turn Emotion Reasoning Score to assess the emotion transitions in multi-turn dialogues. Evaluating seven dialogue systems through continuous, categorical, and perceptual metrics, we show that our framework effectively detects emotional inconsistencies, providing insights for improving current dialogue systems. By releasing a systematic evaluation benchmark, we aim to advance emotion-aware spoken dialogue modeling toward more natural and adaptive interactions.
title EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2508.17623