Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to accurately estimate the RIR from a given reverberant speech signal and the visual cues of its corresponding environment. AV-RIR builds on a novel neural codec-based architecture that effectively captures environment geometry and materials properties and solves speech dereverberation as an auxiliary task by using multi-task learning. We also propose Geo-Mat features that augment material information into visual cues and CRIP that improves late reverberation components in the estimated RIR via image-to-RIR retrieval by 86%. Empirical results show that AV-RIR quantitatively outperforms previous audio-only and visual-only approaches by achieving 36% - 63% improvement across various acoustic metrics in RIR estimation. Additionally, it also achieves higher preference scores in human evaluation. As an auxiliary benefit, dereverbed speech from AV-RIR shows competitive performance with the state-of-the-art in various spoken language processing tasks and outperforms reverberation time error score in the real-world AVSpeech dataset. Qualitative examples of both synthesized reverberant speech and enhanced speech can be found at https://www.youtube.com/watch?v=tTsKhviukAE.

翻译：房间冲激响应（RIR）能捕捉环境的声学特性，其精确估计对语音处理和AR/VR应用至关重要。我们提出AV-RIR，一种新颖的多模态多任务学习方法，旨在从给定的混响语音信号及其对应环境的视觉线索中精确估计RIR。AV-RIR基于创新的神经编解码器架构，该架构有效捕捉环境几何与材质属性，并通过多任务学习将语音去混响作为辅助任务一并解决。我们还提出Geo-Mat特征，用于将材质信息增强至视觉线索中，以及CRIP方法，通过图像到RIR的检索将估计RIR中的晚期混响分量提升86%。实验结果表明，AV-RIR在RIR估计的多种声学指标上相比先前仅依赖音频或视觉的方法实现36%-63%的性能提升，量化表现更优。此外，其在人工评估中亦获得更高偏好分数。作为辅助收益，AV-RIR产生的去混响语音在多种口语语言处理任务中与当前最优方法性能相当，并在真实世界的AVSpeech数据集上超越混响时间误差分数。合成混响语音及增强语音的定性示例可访问https://www.youtube.com/watch?v=tTsKhviukAE。