LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 18617-18629
Abstract
Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, Yang Feng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Language Model Can Listen While SpeakingProceedings of the AAAI Conference on Artificial Intelligence, 2025
- SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training2025
- Recent Advances in Speech Language Models: A Survey2025
- StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning2024
- A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation2024
- Enhancing Chat Language Models by Scaling High-quality Instructional Conversations2023
- SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities2023
- UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 20222022
- The State of Speech in HCI: Trends, Themes and ChallengesInteracting with Computers, 2019
- Connectionist temporal classification2006