Audio-Aware Large Language Models as Judges for Speaking Styles

TL;DR

This paper demonstrates that audio-aware large language models can effectively evaluate speaking styles in speech generation, showing promise as automatic judges comparable to human evaluators.

Contribution

It introduces the use of ALLMs as automatic judges for speaking styles, comparing their assessments with human judgments and highlighting their potential in speech evaluation.

Findings

Gemini-2.5-pro's judgments align with human evaluations.

ALLMs reveal current SLMs' limitations in style control.

ALLMs show promise as reliable speech style evaluators.

Abstract

Audio-aware large language models (ALLMs) can understand the textual and non-textual information in the audio input. In this paper, we explore using ALLMs as an automatic judge to assess the speaking styles of speeches. We use ALLM judges to evaluate the speeches generated by SLMs on two tasks: voice style instruction following and role-playing. The speaking style we consider includes emotion, volume, speaking pace, word emphasis, pitch control, and non-verbal elements. We use four spoken language models (SLMs) to complete the two tasks and use humans and ALLMs to judge the SLMs' responses. We compare two ALLM judges, GPT-4o-audio and Gemini-2.5-pro, with human evaluation results and show that the agreement between Gemini and human judges is comparable to the agreement between human evaluators. These promising results show that ALLMs can be used as a judge to evaluate SLMs. Our results also reveal that current SLMs, even GPT-4o-audio, still have room for improvement in controlling the speaking style and generating natural dialogues.