# VocalBench-DF: A Benchmark for Evaluating Speech LLM Robustness to Disfluency

arXiv: https://arxiv.org/abs/2510.15406 · HTML: https://mlsanity.com/paper/2510.15406/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (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)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix](https://mlsanity.com/paper/2505.13032/) (2025)
- [Baichuan-Omni-1.5 Technical Report](https://mlsanity.com/paper/2501.15368/) (2025)
- [Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities](https://mlsanity.com/paper/2410.11190/) (2024)
- [MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.04779/) (2025)
- [LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis](https://mlsanity.com/paper/2505.02625/) (2025)
- [URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models](https://mlsanity.com/paper/2502.17810/) (2025)
- [VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models](https://mlsanity.com/paper/2505.15727/) (2025)
- [VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation](https://mlsanity.com/paper/2504.04060/) (2025)
- [C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations](https://mlsanity.com/paper/2507.22968/) (2025)

## Built on by (most cited first, 8 of 8)

- [MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes](https://mlsanity.com/paper/2605.06897/) (2026)
- [Pardon? Evaluating Conversational Repair in Large Audio-Language Models](https://mlsanity.com/paper/2601.12973/) (2026)
- [SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue](https://mlsanity.com/paper/2603.16783/) (2026)
- [Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs](https://mlsanity.com/paper/2604.05522/) (2026)
- [Back to Basics: Revisiting ASR in the Age of Voice Agents](https://mlsanity.com/paper/2603.25727/) (2026)
- [CallScreenBench: Benchmarking Small Language Models as Phone Secretaries](https://mlsanity.com/paper/2608.01033/) (2026)
- [The Role of Disfluencies in Speech Translation](https://mlsanity.com/paper/2608.02138/) (2026)
- [Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations](https://mlsanity.com/paper/2608.03970/) (2026)

## Abstract (arXiv)

While Speech Large Language Models (Speech-LLMs) show strong performance in many applications, their robustness is critically under-tested, especially to speech disfluency. Existing evaluations often rely on idealized inputs, overlooking common disfluencies, particularly those associated with conditions like Parkinson's disease. This work investigates whether current Speech-LLMs can maintain performance when interacting with users who have speech impairments. To facilitate this inquiry, we introduce VocalBench-DF, a framework for the systematic evaluation of disfluency across a multi-dimensional taxonomy. Our evaluation of 22 mainstream Speech-LLMs reveals substantial performance degradation, indicating that their real-world readiness is limited. Further analysis identifies phoneme-level processing and long-context modeling as primary bottlenecks responsible for these failures. Strengthening recognition and reasoning capability from components and pipelines can substantially improve robustness. These findings highlight the urgent need for new methods to improve disfluency handling and build truly inclusive Speech-LLMs