STEB - Nonverbal Vocalization Preservation (English to Chinese): leaderboard
Metric: LLM-judged nonverbal-vocalization preservation (1-5): type, count, order and position of events such as laughter in the NV-marked transcripts of the source and the translated speech (BEATs event detection), scored three times by Qwen3-30B-A3B (outlier-aware aggregate); English-to-Chinese speech-to-speech translation of the NV subset's English source utterances. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Step-Audio-2 | 1.38 |
| 2 | UniSS | 1.36 |
| 3 | SeamlessExpressive | 1.23 |
| 4 | Seed LiveInterpret 2.0 | 1.09 |
Interactive version: theaggregate.ai/benchmark?slug=steb-nonverbal-vocalization-preservation-english-to-chinese · How It Works · Data refreshed daily, snapshot 2026-09-26.