Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues. However, most existing approaches rely on precomputed room impulse responses (RIRs) for binaural audio rendering, restricting agents to discrete grid positions and leading to spatially discontinuous observations. To establish a more realistic setting, we introduce Semantic Audio-Visual Navigation in Continuous Environments (SAVN-CE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams. In this setting, targets may intermittently become silent or stop emitting sound entirely, causing agents to lose goal information. To tackle this challenge, we propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memory-augmented goal reasoning. Comprehensive experiments demonstrate that MAGNet significantly outperforms state-of-the-art methods, achieving up to a 12.1\% absolute improvement in success rate. These results also highlight its robustness to short-duration sounds and long-distance navigation scenarios. The code is available at https://github.com/yichenzeng24/SAVN-CE.
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…
UT Austin（德克萨斯大学奥斯汀分校）；Facebook AI Research（Facebook人工智能研究院）
Recent work on audio-visual navigation assumes a constantly-sounding target and restricts the role of audio to signaling the target's position. We introduce semantic audio-visual navigation, where objects in the environment make sounds consistent with their semantic meaning (e.g., toilet flushing, door creaking) and acoustic events are sporadic or short in duration. We propose a transformer-based model to tackle this new semantic AudioGoal task, incorporating an inferred goal descriptor that captures both spatial and semantic properties of the target. Our model's persistent multimodal memory e…
In audio-visual navigation (AVN), an intelligent agent needs to navigate to a constantly sound-making object in complex 3D environments based on its audio and visual perceptions. While existing methods attempt to improve the navigation performance with preciously designed path planning or intricate task settings, none has improved the model generalisation on unheard sounds with task settings unchanged. We thus propose a contrastive learning-based method to tackle this challenge by regularising the audio encoder, where the sound-agnostic goal-driven latent representations can be learnt from var…
UT Austin（德克萨斯大学奥斯汀分校）；Facebook AI Research（脸书人工智能研究院）
In audio-visual navigation, an agent intelligently travels through a complex, unmapped 3D environment using both sights and sounds to find a sound source (e.g., a phone ringing in another room). Existing models learn to act at a fixed granularity of agent motion and rely on simple recurrent aggregations of the audio observations. We introduce a reinforcement learning approach to audio-visual navigation with two key novel elements: 1) waypoints that are dynamically set and learned end-to-end within the navigation policy, and 2) an acoustic memory that provides a structured, spatially grounded r…
UT Austin（德克萨斯大学奥斯汀分校）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Facebook Reality Labs（Facebook 现实实验室）；Facebook AI Research（Facebook 人工智能研究院）
Moving around in the world is naturally a multisensory experience, but today's embodied agents are deaf---restricted to solely their visual perception of the environment. We introduce audio-visual navigation for complex, acoustically and visually realistic 3D environments. By both seeing and hearing, the agent must learn to navigate to a sounding object. We propose a multi-modal deep reinforcement learning approach to train navigation policies end-to-end from a stream of egocentric audio-visual observations, allowing the agent to (1) discover elements of the geometry of the physical space indi…
Audio Spatially-Guided Fusion for Audio-Visual Navigation
Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学联合研究实验室，具身智能）；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国际联合研究实验室）；School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）
Audio-visual navigation combines sight and hearing to navigate to a sound-emitting source in an unmapped environment. While recent approaches have demonstrated the benefits of audio input to detect and find the goal, they focus on clean and static sound sources and struggle to generalize to unheard sounds. In this work, we propose the novel dynamic audio-visual navigation benchmark which requires catching a moving sound source in an environment with noisy and distracting sounds, posing a range of new challenges. We introduce a reinforcement learning approach that learns a robust navigation pol…
University of California, Riverside（加州大学河滨分校）；Mitsubishi Electric Research Labs（三菱电机研究实验室）
Recent years have seen embodied visual navigation advance in two distinct directions: (i) in equipping the AI agent to follow natural language instructions, and (ii) in making the navigable world multimodal, e.g., audio-visual navigation. However, the real world is not only multimodal, but also often complex, and thus in spite of these advances, agents still need to understand the uncertainty in their actions and seek instructions to navigate. To this end, we present AVLEN~ -- an interactive agent for Audio-Visual-Language Embodied Navigation. Similar to audio-visual navigation tasks, the goal…
Audio-Guided Visual Perception for Audio-Visual Navigation
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing（丝绸之路多语种认知计算国际联合实验室）；Tsinghua University（清华大学）；Tianjin University of Technology（天津工业大学）
Audio-visual embodied navigation, as a hot research topic, aims training a robot to reach an audio target using egocentric visual (from the sensors mounted on the robot) and audio (emitted from the target) input. The audio-visual information fusion strategy is naturally important to the navigation performance, but the state-of-the-art methods still simply concatenate the visual and audio features, potentially ignoring the direct impact of context. Moreover, the existing approaches requires either phase-wise training or additional aid (e.g. topology graph and sound semantics). Up till this date…
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Xinjiang University（新疆大学）；JD Explore Academy, JD.com（京东探索研究院）
Audio-visual navigation task requires an agent to find a sound source in a realistic, unmapped 3D environment by utilizing egocentric audio-visual observations. Existing audio-visual navigation works assume a clean environment that solely contains the target sound, which, however, would not be suitable in most real-world applications due to the unexpected sound noise or intentional interference. In this work, we design an acoustically complex environment in which, besides the target sound, there exists a sound attacker playing a zero-sum game with the agent. More specifically, the attacker can…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Tsinghua University（清华大学）；Massachusetts Institute of Technology（麻省理工学院）；Google（谷歌）
A crucial ability of mobile intelligent agents is to integrate the evidence from multiple sensory inputs in an environment and to make a sequence of actions to reach their goals. In this paper, we attempt to approach the problem of Audio-Visual Embodied Navigation, the task of planning the shortest path from a random starting location in a scene to the sound source in an indoor environment, given only raw egocentric visual and audio sensory data. To accomplish this task, the agent is required to learn from various modalities, i.e. relating the audio signal to the visual environment. Here we de…
Tufts University（塔夫茨大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）
Generalisation to unseen contexts remains a challenge for embodied navigation agents. In the context of semantic audio-visual navigation (SAVi) tasks, the notion of generalisation should include both generalising to unseen indoor visual scenes as well as generalising to unheard sounding objects. However, previous SAVi task definitions do not include evaluation conditions on truly novel sounding objects, resorting instead to evaluating agents on unheard sound clips of known objects; meanwhile, previous SAVi methods do not include explicit mechanisms for incorporating domain knowledge about obje…
Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation
Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术创新中心）；School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；School of Electrical Engineering and Automation, Tianjin University of Technology（天津理工大学电气工程与自动化学院）
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）
University of Freiburg（弗赖堡大学）；Google Research（谷歌研究院）；University of Technology Nuremberg（纽伦堡工业大学）
While interacting in the world is a multi-sensory experience, many robots continue to predominantly rely on visual perception to map and navigate in their environments. In this work, we propose Audio-Visual-Language Maps (AVLMaps), a unified 3D spatial map representation for storing cross-modal information from audio, visual, and language cues. AVLMaps integrate the open-vocabulary capabilities of multimodal foundation models pre-trained on Internet-scale data by fusing their features into a centralized 3D voxel grid. In the context of navigation, we show that AVLMaps enable robot systems to i…
Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment
The University of Queensland（昆士兰大学）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）；Matrix Verse AI（矩阵 Verse 人工智能公司）；CSIRO Data61（联邦科学与工业研究组织 Data61 部门）；Macau University of Science and Technology（澳门科技大学）
Spatial-Aware Conditioned Fusion for Audio-Visual Navigation
Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学具身智能联合研究实验室）；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）
Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology, Xinjiang University（新疆多模态智能处理与信息安全工程技术创新中心，计算机科学与技术学院，新疆大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）；School of Electrical Engineering and Automation, Tianjin University of Technology（电气工程与自动化学院，天津工业大学）
CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
Australian Institute for Machine Learning, University of Adelaide（澳大利亚机器学习研究所，阿德莱德大学）；Sony Group Corporation（索尼集团）；Sony AI, Sony Group Corporation（索尼人工智能，索尼集团）
Video summarization attracts attention for efficient video representation, retrieval, and browsing to ease volume and traffic surge problems. Although video summarization mostly uses the visual channel for compaction, the benefits of audio-visual modeling appeared in recent literature. The information coming from the audio channel can be a result of audio-visual correlation in the video content. In this study, we propose a new audio-visual video summarization framework integrating four ways of audio-visual information fusion with GRU-based and attention-based networks. Furthermore, we investig…
Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学具身智能联合研究实验室）；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）
In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the robustness of audio-visual learning. We attack audio, visual, and both modalities to explore whether audio-visual integration still strengthens perception and how different fusion mechanisms affect the robustness of audio-visual models. For interpreting the multimodal interactions under attacks, we learn a weakly-supervised sound source visual localization model to localize sou…
Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance learning. We show that the learnt representations are useful for classifying events and localizing their characteristic audio-visual elements. The system is trained using only video-level event labels without any timing information. An important feature of our method is its capacity to learn from unsynchronized audio-visual events. We achieve state-of-the-art r…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Google Research（谷歌研究院）
Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present AudioScope, a novel audio-visual sound separation framework that can be trained without supervision to isolate on-screen sound sources from real in-the-wild videos. Prior audio-visual separation work assumed artificial limitations on the domain of sound classes (e.g., to speech or music), constrained the number of sources, and required strong sound separation or vis…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions, limiting their application in the complex auditory scene. Towards the cocktail party problem, we propose a novel audio-visual speech separation model. In our model, we use the face detector to detect the number of speakers in the scene and use visual information to avoid the permutation problem. To improve our model's generalization ability to unknown speakers, w…
University of Oxford（牛津大学）；VGG（视觉几何组）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）
Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions. First, we propose a scalable pipeline based on computer vision techniques to create an audio dataset from open-source media. Our pipeline involves obtaining videos from YouTube; using image classification algorithms to localize audio-visual correspondence; and filtering out ambient noise using audio verification. Second, we use this pipeline to…
Cross-modal audio-visual perception has been a long-lasting topic in psychology and neurology, and various studies have discovered strong correlations in human perception of auditory and visual stimuli. Despite works in computational multimodal modeling, the problem of cross-modal audio-visual generation has not been systematically studied in the literature. In this paper, we make the first attempt to solve this cross-modal generation problem leveraging the power of deep generative adversarial training. Specifically, we use conditional generative adversarial networks to achieve cross-modal aud…
The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i.…
Residual Cross-Modal Fusion Networks for Audio-Visual Navigation
School of Computer Science and Technology, Xinjiang University, Urumqi, China（新疆大学计算机科学与技术学院）；Joint International Research Laboratory of Silk Road Multilingual Cognitive（丝绸之路多语认知联合国际实验室）；School of Mechatronic Engineering and Automation Shanghai University, Shanghai, China（上海大学机电工程与自动化学院）
Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics
The University of Queensland（昆士兰大学）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）；Matrix Verse AI；CSIRO Data61（联邦科学与工业研究组织数据61部）；Macau University of Science and Technology（澳门科技大学）
Conventional audio-visual models have independent audio and video branches. In this work, we unify the audio and visual branches by designing a Unified Audio-Visual Model (UAVM). The UAVM achieves a new state-of-the-art audio-visual event classification accuracy of 65.8% on VGGSound. More interestingly, we also find a few intriguing properties of UAVM that the modality-independent counterparts do not have.
Beijing Institute of Technology（北京理工大学）；ETH Zurich（苏黎世联邦理工学院）；University of Technology Sydney（悉尼科技大学）；Yangtze Delta Region Academy of Beijing Institute of Technology（北京理工大学长三角研究院）
With the emergence of varied visual navigation tasks (e.g, image-/object-/audio-goal and vision-language navigation) that specify the target in different ways, the community has made appealing advances in training specialized agents capable of handling individual navigation tasks well. Given plenty of embodied navigation tasks and task-specific solutions, we address a more fundamental question: can we learn a single powerful agent that masters not one but multiple navigation tasks concurrently? First, we propose VXN, a large-scale 3D dataset that instantiates four classic navigation tasks in s…
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）
Australian National University（澳大利亚国立大学）；CSIRO-DATA61（联邦科学与工业研究组织DATA61）；University of Technology Sydney（悉尼科技大学）
Object goal navigation aims to steer an agent towards a target object based on observations of the agent. It is of pivotal importance to design effective visual representations of the observed scene in determining navigation actions. In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation. VTNet is a highly effective structure that embodies two key properties for visual representations: First, the relationships among all the object instances in a scene are exploited; Second, the spatial locations of objects and image regions…
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）；The University of Hong Kong（香港大学）；Shandong University（山东大学）；Peng Cheng Laboratory（鹏城实验室）
Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos often contain numerous audio-visual events with different categories. To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. The problem is challenging as it requires fine-grained audio-visual scene and context understanding. To tackle this problem, we in…
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…
University of British Columbia（不列颠哥伦比亚大学）；Huawei Technologies Canada Co., Ltd（华为技术加拿大有限公司）；University of Victoria（维多利亚大学）
We propose a new framework for extracting visual information about a scene only using audio signals. Audio-based methods can overcome some of the limitations of vision-based methods i.e., they do not require "line-of-sight", are robust to occlusions and changes in illumination, and can function as a backup in case vision/lidar sensors fail. Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps. First, we train a Vector-Quantized Variational Auto-Encoder to learn th…
Tsinghua University（清华大学）；University of Michigan（密歇根大学）；Shanghai Qi Zhi Institute（上海期智研究院）
From the patter of rain to the crunch of snow, the sounds we hear often convey the visual textures that appear within a scene. In this paper, we present a method for learning visual styles from unlabeled audio-visual data. Our model learns to manipulate the texture of a scene to match a sound, a problem we term audio-driven image stylization. Given a dataset of paired audio-visual data, we learn to modify input images such that, after manipulation, they are more likely to co-occur with a given input sound. In quantitative and qualitative evaluations, our sound-based model outperforms label-bas…
This paper focuses on designing a noise-robust end-to-end Audio-Visual Speech Recognition (AVSR) system. To this end, we propose Visual Context-driven Audio Feature Enhancement module (V-CAFE) to enhance the input noisy audio speech with a help of audio-visual correspondence. The proposed V-CAFE is designed to capture the transition of lip movements, namely visual context and to generate a noise reduction mask by considering the obtained visual context. Through context-dependent modeling, the ambiguity in viseme-to-phoneme mapping can be refined for mask generation. The noisy representations a…
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）
UC San Diego（加州大学圣地亚哥分校）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；ShanghaiTech University（上海科技大学）；University of Pennsylvania（宾夕法尼亚大学）
Current audio-visual separation methods share a standard architecture design where an audio encoder-decoder network is fused with visual encoding features at the encoder bottleneck. This design confounds the learning of multi-modal feature encoding with robust sound decoding for audio separation. To generalize to a new instrument: one must finetune the entire visual and audio network for all musical instruments. We re-formulate visual-sound separation task and propose Instrument as Query (iQuery) with a flexible query expansion mechanism. Our approach ensures cross-modal consistency and cross-…
