Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion transformer architecture that enables streaming high-quality spatial audio generation. 2) We design a Spatial Video-Audio Contrastive (SVAC) learning strategy to align the video encoder with the acoustic domain, and further employ a multi-objective online direct preference optimization (ODPO) scheme, resulting in strong spatial perception and robust multimodal spatial audio synthesis. 3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions. Experimental results demonstrate that SwanSphere achieves superior performance in both video-to-spatial and text-to-spatial audio generation tasks. Demos can be found at: https://swanaigc.github.io.

翻译：实时且精确的空间音频生成对于提供沉浸式体验至关重要。然而，现有空间音频合成技术常受限于生成质量与高推理延迟之间的权衡，且难以从多模态输入中捕获精确的空间信息。为应对这些挑战，我们提出SwanSphere——一个统一的流式框架，用于从全景视频和文本提示生成高保真空间音频。SwanSphere的主要贡献如下：1）我们引入一种因果自回归扩散Transformer架构，实现流式高质量空间音频生成。2）我们设计了一种空间视频-音频对比学习（SVAC）策略，用于将视频编码器与声学域对齐，并进一步采用多目标在线直接偏好优化（ODPO）方案，从而实现强大的空间感知能力与鲁棒的多模态空间音频合成。3）为缓解当前空间音频数据集的稀缺问题，我们还开发了一条用于生成详细空间描述的自动标注流水线。实验结果表明，SwanSphere在视频-空间和文本-空间音频生成任务中均实现了优越性能。演示示例请见：https://swanaigc.github.io。