On the Emotion Understanding of Synthesized Speech

ACL ARR 2026 January Submission5739 Authors

Keywords: Speech emotion recognition, Synthesis speech

Abstract:

Emotion is a core paralinguistic feature in voice interaction. It is widely believed that emotion understanding models learn fundamental representations that transfer to synthesized speech, making emotion understanding results a plausible reward or evaluation metric for assessing emotional expressiveness in speech synthesis. In this work, we critically examine this assumption by systematically evaluating Speech Emotion Recognition (SER) on synthesized speech across datasets, discriminative and generative SER models, and diverse synthesis models.
We find that current SER models can not generalize to synthesized speech, largely because speech token prediction during synthesis induces a representation mismatch between synthesized and human speech. Moreover, generative Speech Language Models (SLMs) tend to infer emotion from textual semantics while ignoring paralinguistic cues. Overall, our findings suggest that existing SER models often exploit non-robust shortcuts rather than capturing fundamental features, and paralinguistic understanding in SLMs remains challenging.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: Speech Recognition, Text-to-Speech and Spoken Language Understanding

Contribution Types: Model analysis & interpretability, Data analysis, Position papers

Languages Studied: English

Submission Number: 5739