The framework of visually-guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An ongoing trend in this field has been to tailor involved visual feature extractor for informative visual guidance and separately devise module for feature fusion, while utilizing U-Net by default for sound analysis. However, such divide-and-conquer paradigm is parameter inefficient and, meanwhile, may obtain suboptimal performance as jointly optimizing and harmonizing various model components is challengeable. By contrast, this paper presents a novel approach, dubbed audio-visual predictive coding (AVPC), to tackle this task in a parameter efficient and more effective manner. The network of AVPC features a simple ResNet-based video analysis network for deriving semantic visual features, and a predictive coding-based sound separation network that can extract audio features, fuse multimodal information, and predict sound separation masks in the same architecture. By iteratively minimizing the prediction error between features, AVPC integrates audio and visual information recursively, leading to progressively improved performance. In addition, we develop a valid self-supervised learning strategy for AVPC via co-predicting two audio-visual representations of the same sound source. Extensive evaluations demonstrate that AVPC outperforms several baselines in separating musical instrument sounds, while reducing the model size significantly. Code is available at: https://github.com/zjsong/Audio-Visual-Predictive-Coding.
There exists an unequivocal distinction between the sound produced by a static source and that produced by a moving one, especially when the source moves towards or away from the microphone. In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio. Towards this end, we present Audio Separator and Motion Predictor (ASMP) -- a deep learning framework that leverages the 3D structure of the scene and the motion of sound sources for better audio source separation. At the heart of ASMP is a 2.5D scene graph capturing various objects in the video and their pseudo-3D spatial proximities. This graph is constructed by registering together 2.5D monocular depth predictions from the 2D video frames and associating the 2.5D scene regions with the outputs of an object detector applied on those frames. The ASMP task is then mathematically modeled as the joint problem of: (i) recursively segmenting the 2.5D scene graph into several sub-graphs, each associated with a constituent sound in the input audio mixture (which is then separated) and (ii) predicting the 3D motions of the corresponding sound sources from the separated audio. To empirically evaluate ASMP, we present experiments on two challenging audio-visual datasets, viz. Audio Separation in the Wild (ASIW) and Audio Visual Event (AVE). Our results demonstrate that ASMP achieves a clear improvement in source separation quality, outperforming prior works on both datasets, while also estimating the direction of motion of the sound sources better than other methods.
State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches often ignore the visual context of these sound sources or avoid modeling object interactions that may be useful to better characterize the sources, especially when the same object class may produce varied sounds from distinct interactions. To address this challenging problem, we propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs, each subgraph being associated with a unique sound obtained by co-segmenting the audio spectrogram. At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention. These embeddings are used for conditioning an audio encoder-decoder towards source separation. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds. In this paper, we also introduce an "in the wild'' video dataset for sound source separation that contains multiple non-musical sources, which we call Audio Separation in the Wild (ASIW). This dataset is adapted from the AudioCaps dataset, and provides a challenging, natural, and daily-life setting for source separation. Thorough experiments on the proposed ASIW and the standard MUSIC datasets demonstrate state-of-the-art sound separation performance of our method against recent prior approaches.
The objective of this paper is to perform audio-visual sound source separation, i.e.~to separate component audios from a mixture based on the videos of sound sources. Moreover, we aim to pinpoint the source location in the input video sequence. Recent works have shown impressive audio-visual separation results when using prior knowledge of the source type (e.g. human playing instrument) and pre-trained motion detectors (e.g. keypoints or optical flows). However, at the same time, the models are limited to a certain application domain. In this paper, we address these limitations and make the following contributions: i) we propose a two-stage architecture, called Appearance and Motion network (AMnet), where the stages specialise to appearance and motion cues, respectively. The entire system is trained in a self-supervised manner; ii) we introduce an Audio-Motion Embedding (AME) framework to explicitly represent the motions that related to sound; iii) we propose an audio-motion transformer architecture for audio and motion feature fusion; iv) we demonstrate state-of-the-art performance on two challenging datasets (MUSIC-21 and AVE) despite the fact that we do not use any pre-trained keypoint detectors or optical flow estimators. Project page: https://ly-zhu.github.io/self-supervised-motion-representations
Learning how to localize and separate individual object sounds in the audio channel of the video is a difficult task. Current state-of-the-art methods predict audio masks from artificially mixed spectrograms, known as Mix-and-Separate framework. We propose an audio-visual co-segmentation, where the network learns both what individual objects look and sound like, from videos labeled with only object labels. Unlike other recent visually-guided audio source separation frameworks, our architecture can be learned in an end-to-end manner and requires no additional supervision or bounding box proposals. Specifically, we introduce weakly-supervised object segmentation in the context of sound separation. We also formulate spectrogram mask prediction using a set of learned mask bases, which combine using coefficients conditioned on the output of object segmentation , a design that facilitates separation. Extensive experiments on the MUSIC dataset show that our proposed approach outperforms state-of-the-art methods on visually guided sound source separation and sound denoising.
The objective of this paper is to recover the original component signals from a mixture audio with the aid of visual cues of the sound sources. Such task is usually referred as visually guided sound source separation. The proposed Cascaded Opponent Filter (COF) framework consists of multiple stages, which recursively refine the source separation. A key element in COF is a novel opponent filter module that identifies and relocates residual components between sources. The system is guided by the appearance and motion of the source, and, for this purpose, we study different representations based on video frames, optical flows, dynamic images, and their combinations. Finally, we propose a Sound Source Location Masking (SSLM) technique, which, together with COF, produces a pixel level mask of the source location. The entire system is trained end-to-end using a large set of unlabelled videos. We compare COF with recent baselines and obtain the state-of-the-art performance in three challenging datasets (MUSIC, A-MUSIC, and A-NATURAL). Project page: https://ly-zhu.github.io/cof-net.