---
id: 20260919-T0-06
title: "全双工语音模型工具调用新架构：前端-后端分离方案"
title_en: "Frontend-Backend Architecture Brings Tool Calls to Full-Duplex Speech Models"
url: https://ai.daily.yangsir.net/daily/20260919-T0-06
issue_date: 2026-09-19
publish_date: 2026-09-18T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.19334
---

# 全双工语音模型工具调用新架构：前端-后端分离方案

arXiv论文提出一种前后端分离架构，让全双工语音到语音模型具备调用外部工具和完成语音Agent任务的能力。全双工S2S模型能提供自然、低延迟的对话交互，但此前缺乏工具调用能力。该架构将双工语音模型与工具调用逻辑解耦，具体实现细节和实验数据需参见论文全文。

## English Version

**Frontend-Backend Architecture Brings Tool Calls to Full-Duplex Speech Models**

A paper on arXiv proposes a frontend-backend architecture enabling full-duplex speech-to-speech models to use external tools and complete voice-agent tasks. Full-duplex S2S models offer natural, low-latency conversational interaction but previously lacked tool-use capability. The architecture decouples the duplex speech model from tool-calling logic. Implementation details and experimental data are in the full paper.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.19334)

**详情页**：https://ai.daily.yangsir.net/daily/20260919-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*