Audio-Aware Large Language Models as Judges for Speaking Styles
By: Cheng-Han Chiang , Xiaofei Wang , Chung-Ching Lin and more
Potential Business Impact:
AI judges speaking styles better than people.
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.
Similar Papers
Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
Sound
Helps computers understand if speech sounds good.
AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation
Computation and Language
Lets computers judge speech quality like people.
SpeakerSleuth: Evaluating Large Audio-Language Models as Judges for Multi-turn Speaker Consistency
Computation and Language
Helps AI tell if a speaker's voice changes in talks.