Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
(翻译)构建低延迟多语言语音智能体:借助 NVIDIA Magpie TTS 实现开放权重与完整部署控制
A Blog post by NVIDIA on Hugging Face

(翻译)构建低延迟多语言语音智能体:借助 NVIDIA Magpie TTS 实现开放权重与完整部署控制
A Blog post by NVIDIA on Hugging Face

(翻译)DuplexSpeechBench-IFEval:评估全双工语音智能体中的隐式指令遵循
Abstract page for arXiv paper 2609.03423: DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
(翻译)同日同样叙事;提前一天,信号不同:金融情感分析的双重效度
Abstract page for arXiv paper 2609.11144: Same Day, Same Story; One Day Ahead, a Different Signal: The Dual Validity of Financial Sentiment
(翻译)LLM在草稿-验证-修订流水线中能否解决指示语歧义?
Abstract page for arXiv paper 2609.12162: Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
(翻译)用于嘈杂警察音频的预训练ASR伪标签方法
Abstract page for arXiv paper 2609.30469: Pretrained ASR Pseudo-labeling for Noisy Police Audio
(翻译)Open TTS Leaderboard:面向多语言文本转语音与声音克隆的可扩展评估
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
(翻译)为沙特阿拉伯方言微调 NVIDIA Nemotron,并探索适用于其他语言的路径
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.

(翻译)Falcon-Emirati:当 LLM 学会方言、文化与细微差别
A Blog post by Technology Innovation Institute on Hugging Face

(翻译)推出 Falcon ASR
A Blog post by Technology Innovation Institute on Hugging Face

(翻译)叙事包装如何影响 LLM 拒绝:跨语言基准与防御
Abstract page for arXiv paper 2610.11005: How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense