English(EN) Relative Time Intervals Representation for Word-level Timestamping with Masked Training

SpeechLLMs 增强相对时间戳以提高词级准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

研究人员开发了一种新的方法，用于语音大语言模型（SpeechLLMs）改进词级时间戳预测。该方法用相对时间戳取代传统绝对时间戳，增强了模型的词汇量和泛化能力。混合微调策略结合了特定层的全参数微调和其他层的 LoRA，同时掩码时间戳目标可防止过度依赖真实值，从而获得更稳健的性能。 AI

影响提高了语音模型的时间精度，可能增强需要精确计时的应用程序。

排序理由学术论文，详细介绍了一种用于 SpeechLLMs 的新方法。[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: 45 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种用于 SpeechLLMs 的新方法。[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。

arXiv cs.AI TIER_1 English(EN) · Quanwei Tang, Zhiyu Tang, Xu Li, Dong Zhang, Shoushan, Guodong Zhou · 2026-08-26 04:00

用于词级时间戳的相对时间间隔表示与掩码训练

arXiv:2608.24041v1 Announce Type: new Abstract: Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses this gap by enabling SpeechLLMs t…