← 研踪 PaperTrailarXiv:2611.26000 · v1
Xing-Audio-NVVASR: Scaling and Refining Supervision for Joint Recognition of Speech and Non-Verbal Vocalizations
首次提交 2026-11-19 20:21
版本更新 2026-11-19 20:21
雷达观测 2026-11-20 16:53
摘要
Joint recognition of speech and non-verbal vocalizations (NVVs) is hindered by scarce event-rich training data and inaccurate or missing event labels. We present Xing-Audio-NVVASR, an end-to-end recognizer trained through progressive data mining and iterative supervision refinement. Guided by unified acoustic criteria, two heterogeneous models cross-audit annotations, flagging disagreements for teacher reannotation. To uncover shared omissions that model agreement may conceal, complementary breath detectors screen the entire corpus for human review. Human-confirmed labels accumulate across rounds and are preserved during subsequent refinement. Over five rounds, we refine annotations for 170,000 utterances from public corpora and incorporate 630,000 mined utterances. The resulting corpus of approximately 800,000 utterances is used to train a single 1.7B-parameter model that transcribes speech with inline tags for six NVV classes. Across four human-annotated benchmarks, Xing-Audio-NVVASR ranks first among nine models in both composite score and six-class Macro-F1. It achieves a mean composite score of 64.46, surpassing the strongest comparison model, StepAudio 3 Chat Preview, by 6.03 points, and exceeds the annotation teacher's breathing F1 by 14.40 to 31.57 percentage points. We plan to release the model weights, inference code, four evaluation benchmarks, annotation guidelines, and evaluation code.
作者备注:18 pages, 2 figures
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-19 20:21 · 最新观测版本
Xing-Audio-NVVASR: Scaling and Refining Supervision for Joint Recognition of Speech and Non-Verbal Vocalizations
Joint recognition of speech and non-verbal vocalizations (NVVs) is hindered by scarce event-rich training data and inaccurate or missing event labels. We present Xing-Audio-NVVASR, an end-to-end recognizer trained through progressive data mining and iterative supervision refinement. Guided by unified acoustic criteria, two heterogeneous models cross-audit annotations, flagging disagreements for teacher reannotation. To uncover shared omissions that model agreement may conceal, complementary breath detectors screen the entire corpus for human review. Human-confirmed labels accumulate across rounds and are preserved during subsequent refinement. Over five rounds, we refine annotations for 170,000 utterances from public corpora and incorporate 630,000 mined utterances. The resulting corpus of approximately 800,000 utterances is used to train a single 1.7B-parameter model that transcribes speech with inline tags for six NVV classes. Across four human-annotated benchmarks, Xing-Audio-NVVASR ranks first among nine models in both composite score and six-class Macro-F1. It achieves a mean composite score of 64.46, surpassing the strongest comparison model, StepAudio 3 Chat Preview, by 6.03 points, and exceeds the annotation teacher's breathing F1 by 14.40 to 31.57 percentage points. We plan to release the model weights, inference code, four evaluation benchmarks, annotation guidelines, and evaluation code.
查看此版本解读 →查看此版本原文 ↗