arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00859eess.AS
收藏

深度房间脉冲响应完成

Deep Room Impulse Response Completion

Aalto University(阿尔托大学)

Jackie Lin, Georg Götz, Sebastian J. Schlecht

AI总结:

本研究提出DECOR模型,通过仅利用RIR早期部分生成晚期混响,提升空间音频生成效率。

摘要:

在虚拟现实(VR)和视频游戏中实现沉浸式空间音频需要快速且准确地生成房间脉冲响应(RIRs)以合理重现听觉环境。然而,传统模拟或测量长RIRs的方法要么计算成本高,要么受到信噪比低的挑战。本研究受直接声音和早期反射包含足够房间几何和吸收特性信息的启发。基于此前提,我们提出了一项新的任务,称为“RIR完成”,旨在仅使用响应的早期部分(50毫秒)合成晚期混响。为此,我们引入了DECOR,一种深度神经网络,结构为自编码器,旨在预测过滤噪声序列的多指数衰减包络。DECOR的可解释性使其能够与各种渲染技术集成。所提出的方法与改进的最新网络进行了比较,相同比例的表现显示了RIR完成任务的可行性。RIR完成可以广泛应用于需要快速近似晚期混响的RIR生成任务中。

英文摘要:

Rendering immersive spatial audio in virtual reality (VR) and video games demands a fast and accurate generation of room impulse responses (RIRs) to recreate auditory environments plausibly. However, the conventional methods for simulating or measuring long RIRs are either computationally intensive or challenged by low signal-to-noise ratios. This study is propelled by the insight that direct sound and early reflections encapsulate sufficient information about room geometry and absorption characteristics. Building upon this premise, we propose a novel task termed "RIR completion," aimed at synthesizing the late reverberation given only the early portion (50 ms) of the response. To this end, we introduce DECOR, Deep Exponential Completion Of Room impulse responses, a deep neural network structured as an autoencoder designed to predict multi-exponential decay envelopes of filtered noise sequences. The interpretability of DECOR's output facilitates its integration with diverse rendering techniques. The proposed method is compared against an adapted state-of-the-art network, and comparable performance shows promising results supporting the feasibility of the RIR completion task. The RIR completion can be widely adapted to enhance RIR generation tasks where fast late reverberation approximation is required.

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。

↑