# Audio-Aware Large Language Models as Judges for Speaking Styles

arXiv: https://arxiv.org/abs/2506.05984 · HTML: https://mlsanity.com/paper/2506.05984/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt](https://mlsanity.com/paper/2301.13662/) (2023)
- [Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction](https://mlsanity.com/paper/2502.11946/) (2025)
- [Audio Large Language Models Can Be Descriptive Speech Quality Evaluators](https://mlsanity.com/paper/2501.17202/) (2025)
- [VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models](https://mlsanity.com/paper/2501.04962/) (2025)
- [S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models](https://mlsanity.com/paper/2503.05085/) (2025)
- [Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously](https://mlsanity.com/paper/2306.02044/) (2023)
- [Towards General-Purpose Text-Instruction-Guided Voice Conversion](https://mlsanity.com/paper/2309.14324/) (2023)

## Built on by (most cited first, 17 of 17)

- [Game-Time: Evaluating Temporal Dynamics in Spoken Language Models](https://mlsanity.com/paper/2509.26388/) (2025)
- [VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions](https://mlsanity.com/paper/2509.09716/) (2025)
- [AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering](https://mlsanity.com/paper/2601.14728/) (2026)
- [Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation](https://mlsanity.com/paper/2601.13742/) (2026)
- [UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models](https://mlsanity.com/paper/2510.22588/) (2025)
- [Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents](https://mlsanity.com/paper/2606.11219/) (2026)
- [Investigation for Relative Voice Impression Estimation](https://mlsanity.com/paper/2602.14172/) (2026)
- [Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models](https://mlsanity.com/paper/2604.14920/) (2026)
- [STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity](https://mlsanity.com/paper/2606.25529/) (2026)
- [StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech](https://mlsanity.com/paper/2607.22658/) (2026)
- [Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation](https://mlsanity.com/paper/2608.06718/) (2026)
- [Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models](https://mlsanity.com/paper/2512.23578/) (2025)
- [Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations](https://mlsanity.com/paper/2603.29893/) (2026)
- [ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge](https://mlsanity.com/paper/2606.24648/) (2026)
- [Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models](https://mlsanity.com/paper/2607.13408/) (2026)
- [Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions](https://mlsanity.com/paper/2608.09930/) (2026)
- [Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance](https://mlsanity.com/paper/2609.30773/) (2026)

## Abstract (arXiv)

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.