arXiv 2505.026252025-05-05cs.CLcs.AIcs.SDeess.AS

LLaMA-Omni2：基于LLM的实时语音聊天机器人，具备自回归流式语音合成能力

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院）；Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）

Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, Yang Feng

备注：: Preprint. Project: https://github.com/ictnlp/LLaMA-Omni2

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出LLaMA-Omni 2系列语音语言模型，基于Qwen2.5集成语音编码器与自回归流式语音解码器，仅用200K多轮对话样本即在语音问答和指令遵循任务上超越GLM-4-Voice等先前最优模型，实现高质量实时语音交互。

摘要：

实时、智能且自然的语音交互是下一代人机交互的重要组成部分。近期进展展示了基于大语言模型（LLMs）构建智能语音聊天机器人的潜力。本文介绍了LLaMA-Omni 2，这是一系列参数量从0.5B到14B的语音语言模型（SpeechLMs），能够实现高质量的实时语音交互。LLaMA-Omni 2基于Qwen2.5系列模型构建，集成了语音编码器和自回归流式语音解码器。尽管仅在200K多轮语音对话样本上训练，LLaMA-Omni 2在多个语音问答和语音指令遵循基准上表现出强大性能，超越了此前最先进的SpeechLMs，如GLM-4-Voice，后者基于数百万小时的语音数据训练。

英文摘要：

Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language models (LLMs). In this paper, we introduce LLaMA-Omni 2, a series of speech language models (SpeechLMs) ranging from 0.5B to 14B parameters, capable of achieving high-quality real-time speech interaction. LLaMA-Omni 2 is built upon the Qwen2.5 series models, integrating a speech encoder and an autoregressive streaming speech decoder. Despite being trained on only 200K multi-turn speech dialogue samples, LLaMA-Omni 2 demonstrates strong performance on several spoken question answering and speech instruction following benchmarks, surpassing previous state-of-the-art SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。