Work

LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Year: 2025

Type: conference-paper

Abstract: 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 highquality 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-theart SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data. 1

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-long.912

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

Institutions: Chinese Academy of Sciences, Institute of Computing Technology, University of Chinese Academy of Sciences

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

OpenAlex ID: W4412944968