基于自回归扩散Transformer的流式同步空间音频生成

摘要

实现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面临生成质量与高推理延迟之间的权衡困境，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——一种面向全景视频和文本提示的统一流式框架，可实现高保真空间音频生成。SwanSphere的主要创新包括：1）引入因果自回归扩散变换器架构，支持流式高质量空间音频生成；2）设计空间视-听对比学习策略以对齐视频编码器与声学域，并进一步采用多目标在线直接偏好优化方案，从而获得强空间感知能力与鲁棒的多模态空间音频合成能力；3）为缓解当前空间音频数据集稀缺问题，开发了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在视频到空间音频生成和文本到空间音频生成任务中均取得了卓越性能。演示样例详见：https://swanaigc.github.io。

English

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.