Română(RO) Xiaomi-CocktailASR-1 Technical Report

小米发布基于LLM的嘈杂环境下的ASR系统

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

研究人员推出了一种新颖的端到端自动语音识别（ASR）架构Xiaomi-CocktailASR-1，旨在解决多说话人环境中的“鸡尾酒会问题”。该基于LLM的系统利用声纹提示，无需预先分离即可转录目标说话人的语音，同时保持具有竞争力的单说话人性能，并增加了对缺席目标说话人的关键拒绝能力。该架构还支持链式思考（Chain-of-Thought）推理模式，并在各种基准测试中取得了最先进的结果。 AI

影响该模型有望显著提高在嘈杂、多说话人环境下的ASR性能，造福于语音助手和转录服务等应用。

排序理由该集群包含一篇在arXiv上发表的技术报告，详细介绍了用于自动语音识别的新模型架构。[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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇在arXiv上发表的技术报告，详细介绍了用于自动语音识别的新模型架构。[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: model release, paper; 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 Română(RO) · Yiru Zhang, Hang Su, Lichun Fan, Ying Zeng, Chang Liu, Yifeng Wang, Yuquan Liang, Tao Li, Lian Li, Wenhao Yang, Jian Luan, Cong Zou, Heng Qu · 2026-09-11 04:00

Xiaomi-CocktailASR-1 技术报告

arXiv:2609.11274v1 Announce Type: cross Abstract: Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further adva…

本文如何被排名

报道来源 [1]

Xiaomi-CocktailASR-1 技术报告

相关实体

相关话题