English(EN) Earlybird: Predictive Streaming Speech Recognition in 29M Parameters

Earlybird语音模型可提前90毫秒预测单词

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了Earlybird，这是一种新颖的语音识别模型，通过在单词说出之前进行预测，显著降低了延迟。与在单词完成后输出的传统流式模型不同，Earlybird可以在说话者完成单词之前的90毫秒内预测出该单词，在有声读物上的预测准确率为69%。该模型拥有2900万个参数，还能为正在发音的单词提供置信度分数，并在包括Open ASR Leaderboard在内的各种测试集上优于现有模型。 AI

影响降低语音识别延迟，为语音助手和实时应用程序提供更快的响应。

排序理由详细介绍新模型架构和性能的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 33 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新模型架构和性能的研究论文。[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, model release; 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.CL TIER_1 English(EN) · Sahil Mahendrakar · 2026-11-11 05:00

Earlybird：2900万参数的预测流式语音识别

arXiv:2611.14421v1 Announce Type: cross Abstract: Streaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. For a voice agent every millisecond counts: the sooner the words are outputted, the sooner the agent can start a search …

本文如何被排名

报道来源 [1]

Earlybird：2900万参数的预测流式语音识别

相关实体

相关话题