English(EN) Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR

新方法通过适配器堆叠提升低资源语言语音识别能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种名为顺序适配器堆叠的新方法，以改进低资源语言的自动语音识别（ASR）。该技术涉及将可训练的目标语言适配器叠加在冻结的源语言适配器之上，并基于现有的多语言 ASR 模型（如 Whisper）。实验表明，即使对于阿斯图里亚斯语、阿萨姆语和科萨语等语言，仅用一小时的训练数据，该方法也显著优于完全微调，相对词错误率降低了 5-8%。 AI

影响这项研究可能显著提高 ASR 技术对代表性不足的语言的可访问性和可用性。

排序理由该集群包含一篇详细介绍 ASR 新方法的论文。[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: 15 / 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 ASR 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.CL TIER_1 English(EN) · Thai Thi Thanh Thao Dang, Mengjie Qian, Kate Knill · 2026-09-15 04:00

用于跨语言低资源语音识别的顺序适配器堆叠

arXiv:2609.15758v1 Announce Type: new Abstract: Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed toward high-resource languages and degrades sharply for languages with limited l…

本文如何被排名

报道来源 [1]

用于跨语言低资源语音识别的顺序适配器堆叠

相关实体

相关话题