# Paralinguistic-aware dialogue on ParaS2SBench Synthetic (Human Evaluation) Source: [Paralinguistic-aware dialogue on ParaS2SBench Synthetic (Human Evaluation)]() Collection index: [llms.txt]() Data updated: 2026-03-09T06:59:19.223Z Evaluation of dialogue models focusing on paralinguistic awareness (Age, Emotion, Gender, Sarcasm) using human judgment on the ParaS2SBench Synthetic dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Paralinguistic-aware dialogue | | Dataset (including any stated split) | ParaS2SBench Synthetic (Human Evaluation) | | Metric | Average Paralinguistic Awareness Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Average Paralinguistic Awareness Score](): Higher is better; unit: SCALAR. - [Age Awareness Score](): Higher is better; unit: SCALAR. - [Emotion Awareness Score](): Higher is better; unit: SCALAR. - [Gender Awareness Score](): Higher is better; unit: SCALAR. - [Sarcasm Awareness Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Paralinguistic Awareness Score | Result date | Report paper | | --- | --- | --- | --- | | GPT-TTS | 4.922 | Not recorded | 691566140052cac1dc65d8c4 | | GPT-TTS | 4.844 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio GRPO | 4.407 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio GRPO | 4.303 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio SFT | 4.089 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio SFT | 3.996 | Not recorded | 691566140052cac1dc65d8c4 | | GPT-4o voice mode | 3.564 | Not recorded | 691566140052cac1dc65d8c4 | | Qwen2.5 Omni | 3.538 | Not recorded | 691566140052cac1dc65d8c4 | | Qwen2.5 Omni | 3.483 | Not recorded | 691566140052cac1dc65d8c4 | | GPT-4o voice mode | 3.457 | Not recorded | 691566140052cac1dc65d8c4 | | Whisper-GPT-TTS | 3.23 | Not recorded | 691566140052cac1dc65d8c4 | | GLM 4 | 3.23 | Not recorded | 691566140052cac1dc65d8c4 | | GLM 4 | 3.134 | Not recorded | 691566140052cac1dc65d8c4 | | Whisper-GPT-TTS | 3.102 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio | 2.924 | Not recorded | 691566140052cac1dc65d8c4 | | Kimi-Audio | 2.699 | Not recorded | 691566140052cac1dc65d8c4 | ### GPT-TTS Average Paralinguistic Awareness Score: 4.922. Result ID: 69ae6e916dbb7075b955f635. [Reporting paper]() Recorded evaluation configuration: {"Category":"Topline"}. This record does not assert independent reproduction. ### GPT-TTS Average Paralinguistic Awareness Score: 4.844. Result ID: 69ae6e916dbb7075b955f625. [Reporting paper]() Recorded evaluation configuration: {"Category":"Topline"}. This record does not assert independent reproduction. ### Kimi-Audio GRPO Average Paralinguistic Awareness Score: 4.407. Result ID: 69ae6e916dbb7075b955f624. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ours"}. This record does not assert independent reproduction. ### Kimi-Audio GRPO Average Paralinguistic Awareness Score: 4.303. Result ID: 69ae6e916dbb7075b955f634. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ours"}. This record does not assert independent reproduction. ### Kimi-Audio SFT Average Paralinguistic Awareness Score: 4.089. Result ID: 69ae6e916dbb7075b955f623. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ours"}. This record does not assert independent reproduction. ### Kimi-Audio SFT Average Paralinguistic Awareness Score: 3.996. Result ID: 69ae6e916dbb7075b955f633. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ours"}. This record does not assert independent reproduction. ### GPT-4o voice mode Average Paralinguistic Awareness Score: 3.564. Result ID: 69ae6e916dbb7075b955f62f. [Reporting paper]() Recorded evaluation configuration: {"Category":"Closed Source"}. This record does not assert independent reproduction. ### Qwen2.5 Omni Average Paralinguistic Awareness Score: 3.538. Result ID: 69ae6e916dbb7075b955f630. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. ### Qwen2.5 Omni Average Paralinguistic Awareness Score: 3.483. Result ID: 69ae6e916dbb7075b955f620. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. ### GPT-4o voice mode Average Paralinguistic Awareness Score: 3.457. Result ID: 69ae6e916dbb7075b955f61f. [Reporting paper]() Recorded evaluation configuration: {"Category":"Closed Source"}. This record does not assert independent reproduction. ### Whisper-GPT-TTS Average Paralinguistic Awareness Score: 3.23. Result ID: 69ae6e916dbb7075b955f62e. [Reporting paper]() Recorded evaluation configuration: {"Category":"Baseline"}. This record does not assert independent reproduction. ### GLM 4 Average Paralinguistic Awareness Score: 3.23. Result ID: 69ae6e916dbb7075b955f631. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. ### GLM 4 Average Paralinguistic Awareness Score: 3.134. Result ID: 69ae6e916dbb7075b955f621. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. ### Whisper-GPT-TTS Average Paralinguistic Awareness Score: 3.102. Result ID: 69ae6e916dbb7075b955f61e. [Reporting paper]() Recorded evaluation configuration: {"Category":"Baseline"}. This record does not assert independent reproduction. ### Kimi-Audio Average Paralinguistic Awareness Score: 2.924. Result ID: 69ae6e916dbb7075b955f622. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. ### Kimi-Audio Average Paralinguistic Awareness Score: 2.699. Result ID: 69ae6e916dbb7075b955f632. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Open Source"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.