NVIDIA 新研究：语音模型工具调用性能达 92% 准确率
NVIDIA research papers are on fire recently! Here is another interesting paper where they give full...
NVIDIA 新研究，语音模型工具调用准确率 92%，比 GPT-5 在文本模式下的 85% 还高一点，解决语音代理性能瓶颈。
NVIDIA 的最新研究展示了全双工语音模型在客服任务中的表现。在干净环境下，商业双工语音模型完成 31% 到 51% 的任务，而 GPT-5 在文本模式下能达到 85%。研究指出语音代理性能下降主要源于语音处理流程。解决方案是将决策从语音模型中移出，让前端学习发出委托令牌，将转录文本转发给文本后端 LLM 进行工具调用，再通过轻量级预填充和重复机制接收结果并流式合成语音输出。
NVIDIA research papers are on fire recently! Here is another interesting paper where they give full...
NVIDIA research papers are on fire recently! Here is another interesting paper where they give full-duplex speech models tool calls. (bookmark it) Commercial duplex voice models complete 31 to 51 percent of grounded customer-service tasks under clean conditions. Text agents like GPT-5 reach 85 percent on the same tasks in text mode. Most of what a voice agent loses, it loses in the speech pipeline. The fix routes the decision out of the speech model. The duplex frontend learns to emit a delegation token, forwards streaming transcripts to a text backend LLM for the tool call, and receives the result through a lightweight prefill-and-repeat mechanism before streaming TTS speaks it. Tool-call recall runs 92.0 to 97.2 percent with 81.2 percent accuracy at rejecting irrelevant calls. Turn-taking rate, streaming ASR word error rate and spoken-language intelligence all stay at the no-tool-call baseline. Paper: arxiv.org/abs/2609.19334 Chat with Paper: academy.dair.ai/papers/a-front… 💬 6 🔄 1 ❤️ 9 👀 1880 📊 9 ⚡
- shao__meng09-19 00:21原文
