# Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

arXiv: https://arxiv.org/abs/2501.17202 · HTML: https://mlsanity.com/paper/2501.17202/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 63 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Builds on (most cited first, 30 of 48)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation](https://mlsanity.com/paper/2409.04429/) (2024)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [An Actor-Critic Algorithm for Sequence Prediction](https://mlsanity.com/paper/1607.07086/) (2016)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [AudioBench: A Universal Benchmark for Audio Large Language Models](https://mlsanity.com/paper/2406.16020/) (2024)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild](https://mlsanity.com/paper/2403.16973/) (2024)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing](https://mlsanity.com/paper/2309.00916/) (2023)
- [SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation](https://mlsanity.com/paper/2310.09424/) (2023)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)

## Built on by (most cited first, 25 of 25)

- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge](https://mlsanity.com/paper/2505.23009/) (2025)
- [AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation](https://mlsanity.com/paper/2507.12705/) (2025)
- [Audio-Aware Large Language Models as Judges for Speaking Styles](https://mlsanity.com/paper/2506.05984/) (2025)
- [SpeechJudge: Towards Human-Level Judgment for Speech Naturalness](https://mlsanity.com/paper/2511.07931/) (2025)
- [AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering](https://mlsanity.com/paper/2601.14728/) (2026)
- [Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators](https://mlsanity.com/paper/2505.18601/) (2025)
- [MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation](https://mlsanity.com/paper/2603.22677/) (2026)
- [Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought](https://mlsanity.com/paper/2502.18186/) (2025)
- [From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling](https://mlsanity.com/paper/2510.00743/) (2025)
- [Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions](https://mlsanity.com/paper/2602.05220/) (2026)
- [JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions](https://mlsanity.com/paper/2605.04505/) (2026)
- [Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation](https://mlsanity.com/paper/2607.13477/) (2026)
- [Calibration-Reasoning Framework for Descriptive Speech Quality Assessment](https://mlsanity.com/paper/2603.10175/) (2026)
- [Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models](https://mlsanity.com/paper/2604.14920/) (2026)
- [SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models](https://mlsanity.com/paper/2606.25990/) (2026)
- [A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents](https://mlsanity.com/paper/2607.07985/) (2026)
- [SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?](https://mlsanity.com/paper/2601.04029/) (2026)
- [LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2603.13952/) (2026)
- [Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2604.13804/) (2026)
- [Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data](https://mlsanity.com/paper/2606.13507/) (2026)
- [Augmenting Dysarthric Speech Severity Assessment with MOS Supervision](https://mlsanity.com/paper/2606.18645/) (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)
- [AcoustiClaim: A Numeric Claim Benchmark with Instrument Ground Truth](https://mlsanity.com/paper/2609.30483/) (2026)

## Abstract (arXiv)

An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs remain unaware of the quality of the speech they process. This limitation arises because speech quality evaluation is typically excluded from multi-task training due to the lack of suitable datasets. To address this, we introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. In addition to the overall Mean Opinion Score (MOS), this corpus offers detailed analysis across multiple dimensions and identifies causes of quality degradation. It also enables descriptive comparisons between two speech samples (A/B tests) with human-like judgment. Leveraging this corpus, we propose an alignment approach with LLM distillation (ALLD) to guide the audio LLM in extracting relevant information from raw speech and generating meaningful responses. Experimental results demonstrate that ALLD outperforms the previous state-of-the-art regression model in MOS prediction, with a mean square error of 0.17 and an A/B test accuracy of 98.6%. Additionally, the generated responses achieve BLEU scores of 25.8 and 30.2 on two tasks, surpassing the capabilities of task-specific models. This work advances the comprehensive perception of speech signals by audio LLMs, contributing to the development of real-world auditory and sensory intelligent agents.