English(EN) X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR

新的X2Streaming-ASR系统大幅降低语音识别延迟

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了X2Streaming-ASR，这是一种用于流式自动语音识别（ASR）的新型系统，专为实时应用而设计。与使用固定块大小或目标延迟的现有方法不同，X2Streaming-ASR优化了何时提交部分转录内容以及使用何种上下文。这种三阶段训练方法显著降低了提交延迟，在AISHELL-1/2/3和WenetSpeech等基准数据集上低至27-84毫秒，同时与基线系统相比，字符错误率也有所提高。 AI

影响这种新的流式ASR方法可以实现更具响应性和准确性的实时语音代理和对话系统。

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论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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: 14 / 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。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Zhiwei Lin, Kaiqi Fu, Rime Wen, Zehan Liu, Shawn Qin, Roy Gan, Hao Wang, Qian Wang · 2026-09-10 04:00

X2Streaming-ASR：不确定时等待，准备好流式传输 ASR 时发出

arXiv:2609.08672v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems commonly use a fixed chunk size, look-ahead, or t…

本文如何被排名

报道来源 [1]

X2Streaming-ASR：不确定时等待，准备好流式传输 ASR 时发出

相关实体

相关话题