English(EN) Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR

新的GRPO方法提高了半监督ASR的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-26 04:00

研究人员提出了一种名为组相对策略优化（GRPO）的新方法，用于半监督自动语音识别（ASR）。该方法使用教师模型生成的伪标签作为奖励参考，而不是直接作为微调的目标。在银行业领域的实验表明，即使使用来自不同教师模型和语言的嘈杂伪标签，GRPO在标准监督微调方面也实现了显著的相对词错误率改进。 AI

影响这项研究为在转录数据有限的情况下将ASR系统适应新领域提供了一种更稳健的方法，有可能提高准确性并降低成本。

排序理由详细介绍半监督ASR新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍半监督ASR新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Shashi Kumar, Yanis Labrak, Sergio Burdisso, Esa\'u Villatoro-Tello, Petr Motlicek, Kadri Hacioglu, Andreas Stolcke · 2026-10-26 04:00

伪标签作为奖励而非目标：半监督ASR的组相对策略优化

arXiv:2610.32572v1 Announce Type: new Abstract: Adapting ASR to a domain with only untranscribed audio typically relies on pseudo-labeling, a strong teacher transcribes the audio and a student is fine-tuned on it. Because supervised fine-tuning (SFT) treats every pseudo-label tok…