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

TL;DR

This paper introduces EMO-Reasoning, a comprehensive benchmark for evaluating emotional reasoning in spoken dialogue systems, utilizing a new dataset and metrics to identify emotional inconsistencies and improve system naturalness.

Contribution

It presents a novel benchmark and dataset for assessing emotional reasoning in dialogue systems, addressing the lack of holistic evaluation tools for emotion-aware interactions.

Findings

Effective detection of emotional inconsistencies in dialogue systems

Benchmark facilitates comparison of emotional reasoning capabilities

Provides insights for enhancing emotion-aware dialogue modeling

Abstract

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.