Covo-Audio技术报告
Covo-Audio Technical Report
AI总结：
Covo-Audio是一款7B参数端到端LALM，通过大规模预训练和微调在多种任务中表现优异，包括语音文本建模、对话、语音理解等，并展示了其在实际对话助理中的应用潜力。
摘要：
在本文中，我们介绍了Covo-Audio，一款7B参数端到端LALM，能够直接处理连续音频输入并生成音频输出，其在统一架构中实现。通过大规模定制预训练和目标后训练，Covo-Audio在广泛的任务中达到最先进的或具有竞争力的性能，包括语音-文本建模、口语对话、语音理解、音频理解以及全双工语音交互。广泛的评估显示，预训练的基础模型在多个基准上表现出强大的语音-文本理解和语义推理能力，优于同类开源模型。此外，Covo-Audio-Chat，面向对话的变体，展示了强大的口语对话能力，包括理解、上下文推理、指令遵循以及生成合适且富有同理心的响应，验证了其在实际对话助理场景中的适用性。Covo-Audio-Chat-FD，进化后的全双工模型，在口语对话能力和全双工交互行为上实现了显著优于现有模型的性能，展示了其在实际鲁棒性中的能力。为降低端到端LALM在自然对话系统中的部署成本，我们提出了一种智能-说话人解耦策略，将对话智能与语音渲染分离，使在少量文本到语音（TTS）数据下实现灵活的语音定制的同时保持对话性能。总体而言，我们的结果突显了7B规模模型在整合复杂音频智能与高级语义推理方面的强大潜力，并建议了一条通往更强大和多功能LALM的可扩展路径。
英文摘要：
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.
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。
