Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic labelling of sound-making objects, purely based on binaural sounds. 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 a vision `teacher' method and a sound `student' method -- the student method is trained to generate the same results as the teacher method. This way, the auditory system can be trained without using human annotations. We also propose two auxiliary tasks namely, a) a novel task on Spatial Sound Super-resolution to increase the spatial resolution of sounds, and b) dense depth prediction of the scene. We then formulate the three tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results on the dataset show that 1) our method achieves promising results for semantic prediction and the two auxiliary tasks; and 2) the three tasks are mutually beneficial -- training them together achieves the best performance and 3) the number and orientations of microphones are both important. The data and code will be released to facilitate the research in this new direction.
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）
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.…
ETH Zurich（苏黎世联邦理工学院）；MPI for Informatics（马克斯·普朗克信息学研究所）；KU Leuven（鲁汶大学）
Different self-supervised tasks (SSL) reveal different features from the data. The learned feature representations can exhibit different performance for each downstream task. In this light, this work aims to combine Multiple SSL tasks (Multi-SSL) that generalizes well for all downstream tasks. Specifically, for this study, we investigate binaural sounds and image data in isolation. For binaural sounds, we propose three SSL tasks namely, spatial alignment, temporal synchronization of foreground objects and binaural audio and temporal gap prediction. We investigate several approaches of Multi-SS…
National Taiwan University（台湾大学）；ASUS Intelligent Cloud Services（华硕智能云服务）
Human perceives rich auditory experience with distinct sound heard by ears. Videos recorded with binaural audio particular simulate how human receives ambient sound. However, a large number of videos are with monaural audio only, which would degrade the user experience due to the lack of ambient information. To address this issue, we propose an audio spatialization framework to convert a monaural video into a binaural one exploiting the relationship across audio and visual components. By preserving the left-right consistency in both audio and visual modalities, our learning strategy can be vie…
INRIA Grenoble Rhône-Alpes（法国国家信息与自动化研究所格勒诺布尔-罗纳-阿尔卑斯分所）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Technion-Israel Inst. of Technology（以色列理工学院）
This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on monaural segregation. The method starts with a training stage that establishes a locally-linear Gaussian regression model between the directional coordinates of all the sources and the auditory features extracted from binaural measurements. While fixed-length wide-spectrum sounds (w…
Generalizable Audio-Visual Navigation via Binaural Difference Attention and Action Transition Prediction
Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学联合具身智能研究实验室）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语言认知计算联合国际研究实验室）；School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Department of Computer Science, The University of Texas at Dallas（德克萨斯大学达拉斯分校计算机科学系）
Interactive audio spatialization technology previously developed for video game authoring and rendering has evolved into an essential component of platforms enabling shared immersive virtual experiences for future co-presence, remote collaboration and entertainment applications. New wearable virtual and augmented reality displays employ real-time binaural audio computing engines rendering multiple digital objects and supporting the free navigation of networked participants or their avatars through a juxtaposition of environments, real and virtual, often referred to as the Metaverse. These appl…
Reliability-Aware Geometric Fusion for Robust Audio-Visual Navigation
Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学联合具身智能研究实验室）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语种认知计算联合国际研究实验室）；School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）
Sound event detection (SED) and Acoustic scene classification (ASC) are two widely researched audio tasks that constitute an important part of research on acoustic scene analysis. Considering shared information between sound events and acoustic scenes, performing both tasks jointly is a natural part of a complex machine listening system. In this paper, we investigate the usefulness of several spatial audio features in training a joint deep neural network (DNN) model performing SED and ASC. Experiments are performed for two different datasets containing binaural recordings and synchronous sound…
Recent work on audio-visual navigation targets a single static sound in noise-free audio environments and struggles to generalize to unheard sounds. We introduce the novel dynamic audio-visual navigation benchmark in which an embodied AI agent must catch a moving sound source in an unmapped environment in the presence of distractors and noisy sounds. We propose an end-to-end reinforcement learning approach that relies on a multi-modal architecture that fuses the spatial audio-visual information from a binaural audio signal and spatial occupancy maps to encode the features needed to learn a rob…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Stanford University（斯坦福大学）；Facebook AI Research（Facebook 人工智能研究院）
Binaural audio provides human listeners with an immersive spatial sound experience, but most existing videos lack binaural audio recordings. We propose an audio spatialization method that draws on visual information in videos to convert their monaural (single-channel) audio to binaural audio. Whereas existing approaches leverage visual features extracted directly from video frames, our approach explicitly disentangles the geometric cues present in the visual stream to guide the learning process. In particular, we develop a multi-task framework that learns geometry-aware features for binaural a…
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）
Stereophonic audio, especially binaural audio, plays an essential role in immersive viewing environments. Recent research has explored generating visually guided stereophonic audios supervised by multi-channel audio collections. However, due to the requirement of professional recording devices, existing datasets are limited in scale and variety, which impedes the generalization of supervised methods in real-world scenarios. In this work, we propose PseudoBinaural, an effective pipeline that is free of binaural recordings. The key insight is to carefully build pseudo visual-stereo pairs with mo…
The University of Texas at Austin（得克萨斯大学奥斯汀分校）；Facebook AI Research（Facebook人工智能研究院）
Binaural audio provides a listener with 3D sound sensation, allowing a rich perceptual experience of the scene. However, binaural recordings are scarcely available and require nontrivial expertise and equipment to obtain. We propose to convert common monaural audio into binaural audio by leveraging video. The key idea is that visual frames reveal significant spatial cues that, while explicitly lacking in the accompanying single-channel audio, are strongly linked to it. Our multi-modal approach recovers this link from unlabeled video. We devise a deep convolutional neural network that learns to…
Technical University of Denmark（丹麦技术大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Inspired by sophisticated echolocation abilities found in nature, we train a generative adversarial network to predict plausible depth maps and grayscale layouts from sound. To achieve this, our sound-to-vision model processes binaural echo-returns from chirping sounds. We build upon previous work with BatVision that consists of a sound-to-vision model and a self-collected dataset using our mobile robot and low-cost hardware. We improve on the previous model by introducing several changes to the model, which leads to a better depth and grayscale estimation, and increased perceptual quality. Ra…
Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fus…
Zhejiang University（浙江大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Innovation Institute（上海创新研究院）；Stanford University（斯坦福大学）；Beihang University（北航）；The Chinese University of Hong Kong（香港中文大学）
