大型音频语言模型音频令牌压缩技术探索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-21 04:00

研究人员开发了压缩大型音频语言模型（LALMs）音频令牌序列的方法，解决了当前音频编码器的高计算成本问题。探索了无监督分割和平均池化等技术，并结合低秩适配器进行微调，以在大型语言模型处理之前减少音频令牌的数量。这些压缩后的LALMs在自动语音识别和语音到语音翻译任务上，在实现输入音频令牌数量减少高达三倍的同时，表现出与帧级模型相当的性能。 AI

影响有望降低音频密集型AI应用的计算成本并提高可扩展性。

排序理由该集群包含一篇详细介绍新研究方法的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新研究方法的学术论文。[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, infra; 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: 48 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]

arXiv cs.AI TIER_1 English(EN) · Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass · 2026-08-21 04:00

面向大型音频语言模型中的音频令牌压缩

arXiv:2511.20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.g., 25 tokens/s), making attention computation costly and limitin…

本文如何被排名

报道来源 [1]

面向大型音频语言模型中的音频令牌压缩

相关实体

相关话题