Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Wenfu, Li, Chenxing, Zhang, Liqiang, Zhao, Yiyang, Zou, Yuxiang, Li, Hanzhao, Cui, Mingyu, Zhang, Hao, Wei, Kun, Xu, Le, Huang, Zikang, Xu, Jiajun, Hu, Jiliang, He, Xiang, Xie, Zeyu, Kang, Jiawen, Chen, Youjun, Yu, Meng, Yu, Dong, Chen, Rilin, Di, Linlin, Feng, Shulin, Hu, Na, Liu, Yang, Wang, Bang, Yang, Shan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.09823
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917344076365824
author Wang, Wenfu
Li, Chenxing
Zhang, Liqiang
Zhao, Yiyang
Zou, Yuxiang
Li, Hanzhao
Cui, Mingyu
Zhang, Hao
Wei, Kun
Xu, Le
Huang, Zikang
Xu, Jiajun
Hu, Jiliang
He, Xiang
Xie, Zeyu
Kang, Jiawen
Chen, Youjun
Yu, Meng
Yu, Dong
Chen, Rilin
Di, Linlin
Feng, Shulin
Hu, Na
Liu, Yang
Wang, Bang
Yang, Shan
author_facet Wang, Wenfu
Li, Chenxing
Zhang, Liqiang
Zhao, Yiyang
Zou, Yuxiang
Li, Hanzhao
Cui, Mingyu
Zhang, Hao
Wei, Kun
Xu, Le
Huang, Zikang
Xu, Jiajun
Hu, Jiliang
He, Xiang
Xie, Zeyu
Kang, Jiawen
Chen, Youjun
Yu, Meng
Yu, Dong
Chen, Rilin
Di, Linlin
Feng, Shulin
Hu, Na
Liu, Yang
Wang, Bang
Yang, Shan
contents In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.
format Preprint
id arxiv_https___arxiv_org_abs_2602_09823
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Covo-Audio Technical Report
Wang, Wenfu
Li, Chenxing
Zhang, Liqiang
Zhao, Yiyang
Zou, Yuxiang
Li, Hanzhao
Cui, Mingyu
Zhang, Hao
Wei, Kun
Xu, Le
Huang, Zikang
Xu, Jiajun
Hu, Jiliang
He, Xiang
Xie, Zeyu
Kang, Jiawen
Chen, Youjun
Yu, Meng
Yu, Dong
Chen, Rilin
Di, Linlin
Feng, Shulin
Hu, Na
Liu, Yang
Wang, Bang
Yang, Shan
Sound
Computation and Language
Audio and Speech Processing
In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.
title Covo-Audio Technical Report
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2602.09823