English(EN) Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR

新的语音识别方法提高了准确性和延迟

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

研究人员开发了一种新的流式自动语音识别（ASR）方法，该方法提高了转录准确性和延迟。该方法称为AWED，使用词级发射延迟指标和新颖的奖励函数来联合优化转录质量和速度。在测试中，AWED训练的模型在各种前瞻预算下显著优于其基线，降低了词错误率和感知延迟。 AI

影响这项研究可能带来更具响应性和准确性的实时语音应用程序。

排序理由该集群包含一篇详细介绍自动语音识别新方法的 ist 研究论文。[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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍自动语音识别新方法的 ist 研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Xiuwen Zheng · 2026-09-17 04:00

少看多听：流式语音识别的联合奖励GRPO

arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has become the dominant paradigm for streaming large audio-language…