# S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models

arXiv: https://arxiv.org/abs/2503.05085 · HTML: https://mlsanity.com/paper/2503.05085/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities](https://mlsanity.com/paper/2406.11768/) (2024)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech](https://mlsanity.com/paper/2309.09510/) (2023)
- [SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words](https://mlsanity.com/paper/2406.13340/) (2024)
- [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://mlsanity.com/paper/2402.01912/) (2024)
- [Language Model Can Listen While Speaking](https://mlsanity.com/paper/2408.02622/) (2024)
- [speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment](https://mlsanity.com/paper/2104.01378/) (2021)

## Built on by (most cited first, 16 of 16)

- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2505.15957/) (2025)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [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)
- [MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols](https://mlsanity.com/paper/2508.18240/) (2025)
- [EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models](https://mlsanity.com/paper/2510.22758/) (2025)
- [VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions](https://mlsanity.com/paper/2509.09716/) (2025)
- [MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions](https://mlsanity.com/paper/2507.10859/) (2025)
- [BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution](https://mlsanity.com/paper/2510.08697/) (2025)
- [Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation](https://mlsanity.com/paper/2601.13742/) (2026)
- [LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model](https://mlsanity.com/paper/2508.15418/) (2025)
- [SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation](https://mlsanity.com/paper/2604.20842/) (2026)
- [RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems](https://mlsanity.com/paper/2607.14846/) (2026)
- [VoiceLongMemEval: Do Assistants Remember How You Sounded?](https://mlsanity.com/paper/2609.00570/) (2026)
- [DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents](https://mlsanity.com/paper/2609.03423/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have fundamentally reshaped speech-to-speech (S2S) systems, enabling increasingly natural spoken interaction. However, existing benchmarks still rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits, which are central to expressive and human-like communication. We introduce S2S-Arena, a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression. S2S-Arena features a four-level interaction protocol that systematically probes models under increasing paralinguistic complexity, a two-stage data construction pipeline that produces 1,243 speech samples spanning 100+ real-world tasks, and an arena-style evaluation framework that enables reference-free, pairwise comparison directly in the speech modality. Benchmarking 10 state-of-the-art S2S systems over 1,000+ comparisons reveals substantial performance gaps (especially under complex paralinguistic demands) between current academic and industrial systems. Our analysis further identifies key design factors governing expressive instruction following, providing actionable insights for building more natural, robust, and human-aligned speech agents.