arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02763cs.SDcs.CVeess.AS
收藏

双耳SoundNet:用双耳声音预测语义、深度和运动

Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds

MPI for Informatics(马克斯·普朗克信息学研究所);ETH Zürich(苏黎世联邦理工学院);Czech Technical University(捷克技术大学);KU Leuven(鲁汶大学)

Dengxin Dai, Arun Balajee Vasudevan, Jiri Matas, Luc Van Gool

摘要:

人类可以通过使用视觉和/或听觉线索来鲁棒地识别和定位对象。虽然机器已经能够对视觉数据做同样的事情,但对声音做的工作较少。这项工作开发了一种纯粹基于双耳声音的场景理解方法。所考虑的任务包括预测发声对象的语义掩码、发声对象的运动和场景的深度图。为此,我们提出了一种新的传感器设置,并记录了一个新的视听数据集的街道场景与八个专业的双耳麦克风和360度摄像头。视觉和听觉提示的共存被用于监督转移。特别是,我们采用了一个跨模态蒸馏框架,该框架由多个视觉教师方法和一个声音学生方法组成-学生方法经过训练,可以生成与教师方法相同的结果。这样,可以在不使用人类注释的情况下训练听觉系统。为了进一步提高性能,我们提出了另一个新的辅助任务,创造空间声音超分辨率,以提高声音的方向分辨率。然后,我们将这四个任务制定为一个端到端的可训练多任务网络,旨在提高整体性能。实验结果表明:1)我们的方法对所有四个任务都取得了良好的效果,2)这四个任务是互利的-一起训练它们可以获得最佳性能,3)麦克风的数量和方向都很重要,4)从标准频谱图中学习的特征和经典信号处理管道获得的特征对于听觉感知任务是互补的。数据和代码已发布。

英文摘要:

Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done with sounds. This work develops an approach for scene understanding purely based on binaural sounds. The considered tasks include predicting the semantic masks of sound-making objects, the motion of sound-making objects, and the depth map of the scene. To this aim, we propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360-degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framework that consists of multiple vision teacher methods and a sound student method -- the student method is trained to generate the same results as the teacher methods do. This way, the auditory system can be trained without using human annotations. To further boost the performance, we propose another novel auxiliary task, coined Spatial Sound Super-Resolution, to increase the directional resolution of sounds. We then formulate the four tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results show that 1) our method achieves good results for all four tasks, 2) the four tasks are mutually beneficial -- training them together achieves the best performance, 3) the number and orientation of microphones are both important, and 4) features learned from the standard spectrogram and features obtained by the classic signal processing pipeline are complementary for auditory perception tasks. The data and code are released.

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。

↑