arXiv 2610.28711 · cs.SD · 2026-10-20
Qwen-Audio-3.1-ASR Technical Report
Chuanmeng Bian, Daren Chen, Peixin Chen, Zhigao Chen, Chong Deng, Zhiyun Fan, Zhifu Gao, Bo Gong 等 48 人
机构待核实
在最新榜 #352 本站收录于 2026-10-24
一句话要点
Qwen-Audio-3.1-ASR 技术报告：在 3.0 基础上改进语音识别，新增说话人分离转写和通用音频理解；支持 30 种语言和 16 种中文方言，以及历史上下文、分层热词、原生转写润色等指令控制能力，分离转写输出说话人标签和时间戳。
Qwen-Audio-3.1-ASR technical report: building on 3.0 with better speech recognition plus speaker-diarized transcription and general audio understanding; supports 30 languages and 16 Chinese dialects, instruction controls such as historical context, hierarchical hotwords and transcription polishing, with speaker labels and timestamps in diarized output.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲556
- LoopVL: Recurrent Visual Intelligence ▲417
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models ▲270
- UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement ▲266
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。