PulseAugur
中
实时 18:06:09
English(EN) SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces

新的SoniSpeech数据集推动开放词汇静默语音识别发展

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出SoniSpeech，一个新推出的、大规模的、开放词汇的数据集，专为可穿戴静默语音界面（SSIs）设计。这个三模态数据集同步了超声回波图谱、语音音频和前置视频，捕捉了语音和静默语音。SoniSpeech包含18,000个话语，总计34小时，源自SODA对话数据集，具有当代对话式英语，包含超过5,000个独特单词和完整的音素覆盖。一个使用CTC基础的ResNet-34的基线模型在静默语音识别任务上达到了26.3%的词错误率，为这个新兴领域建立了第一个基准。 AI

影响 该数据集有望加速开发更通用、侵入性更小的静默语音界面。

排序理由 该集群包含一篇介绍特定AI任务新数据集和基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

新的SoniSpeech数据集推动开放词汇静默语音识别发展

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇介绍特定AI任务新数据集和基准的研究论文。[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, 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
95 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Ruidong Zhang, Jiacheng Liu, Fran\c{c}ois Guimbreti\`ere, Cheng Zhang ·

    SoniSpeech：面向可穿戴静默语音界面的大规模开放词汇三模态数据集

    arXiv:2608.00803v1 Announce Type: cross Abstract: Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardware such as facial electrodes. We present SoniSpeech, the first large-scale, open-…

相关实体

相关话题