In this paper, we consider the problem of audio-visual synchronisation applied to videos `in-the-wild' (ie of general classes beyond speech). As a new task, we identify and curate a test set with high audio-visual correlation, namely VGG-Sound Sync. We compare a number of transformer-based architectural variants specifically designed to model audio and visual signals of arbitrary length, while significantly reducing memory requirements during training. We further conduct an in-depth analysis on the curated dataset and define an evaluation metric for open domain audio-visual synchronisation. We apply our method on standard lip reading speech benchmarks, LRS2 and LRS3, with ablations on various aspects. Finally, we set the first benchmark for general audio-visual synchronisation with over 160 diverse classes in the new VGG-Sound Sync video dataset. In all cases, our proposed model outperforms the previous state-of-the-art by a significant margin.
Tampere University（坦佩雷大学）；Coop. Medianet Innovation Center（合作媒体网创新中心）；Shanghai Jiao Tong University（上海交通大学）；University of Oxford（牛津大学）
The objective of this paper is audio-visual synchronisation of general videos 'in the wild'. For such videos, the events that may be harnessed for synchronisation cues may be spatially small and may occur only infrequently during a many seconds-long video clip, i.e. the synchronisation signal is 'sparse in space and time'. This contrasts with the case of synchronising videos of talking heads, where audio-visual correspondence is dense in both time and space. We make four contributions: (i) in order to handle longer temporal sequences required for sparse synchronisation signals, we design a mul…
National University of Singapore（新加坡国立大学）；Wuhan University（武汉大学）
Audio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are quite different from in-the-wild videos in many scenarios such as movies, documentaries, and audience sitcoms. To develop diarization methods for these challenging videos, we create the AVA Audio-Visual Diarization (AVA-AVD) dataset. Our experiments demonstrate that adding AVA-AVD into training set can produce significantly better diarization models for in-th…
Beijing University of Posts and Telecommunications（北京邮电大学）；Tencent Inc（腾讯公司）
It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification. Here, we proposed a novel audio-visual strategy that considers aggregators from a fusion perspective. First, we introduced weight-enhanced attentive statistics pooling for the first time in face verification. We find that a strong correlation exists between modalities during pooling, so joint attentive pooling is proposed which contains cycle consistency to learn the implicit inter-frame weight. Finally, each modality is fused with a gated attention mechanism to gain rob…
University of South Carolina（南卡罗来纳大学）；Innopeak Technology Inc.（Innopeak科技公司）；Sigma Technologies（12西格玛科技公司）；JD.com, Inc.（京东集团）；University of Washington Bothell（华盛顿大学博塞尔分校）
Emotion recognition plays an important role in human-computer interaction (HCI) and has been extensively studied for decades. Although tremendous improvements have been achieved for posed expressions, recognizing human emotions in "close-to-real-world" environments remains a challenge. In this paper, we proposed two strategies to fuse information extracted from different modalities, i.e., audio and visual. Specifically, we utilized LBP-TOP, an ensemble of CNNs, and a bi-directional LSTM (BLSTM) to extract features from the visual channel, and the OpenSmile toolkit to extract features from the …
Instituto de Telecomunicações（电信研究所）；University of Beira Interior（贝拉Interior大学）
Current Active Speaker Detection (ASD) models achieve great results on AVA-ActiveSpeaker (AVA), using only sound and facial features. Although this approach is applicable in movie setups (AVA), it is not suited for less constrained conditions. To demonstrate this limitation, we propose a Wilder Active Speaker Detection (WASD) dataset, with increased difficulty by targeting the two key components of current ASD: audio and face. Grouped into 5 categories, ranging from optimal conditions to surveillance settings, WASD contains incremental challenges for ASD with tactical impairment of audio and f…
In this paper, we address the problem of lip-voice synchronisation in videos containing human face and voice. Our approach is based on determining if the lips motion and the voice in a video are synchronised or not, depending on their audio-visual correspondence score. We propose an audio-visual cross-modal transformer-based model that outperforms several baseline models in the audio-visual synchronisation task on the standard lip-reading speech benchmark dataset LRS2. While the existing methods focus mainly on lip synchronisation in speech videos, we also consider the special case of the sing…
University of Oxford（牛津大学）；Naver Corporation（Naver公司）
The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxCo…
University of Edinburgh（爱丁堡大学）；University of Science and Technology of China（中国科学技术大学）；Queen Margaret University（玛格丽特女王大学）；Articulate Instruments Ltd.（Articulate仪器有限公司）
We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound tongue imaging, and lip videos. TaL consists of two parts: TaL1 is a set of six recording sessions of one professional voice talent, a male native speaker of English; TaL80 is a set of recording sessions of 81 native speakers of English without voice talent experience. Overall, the corpus contains 24 hours of parallel ultrasound, video, and audio data, of which approximately 13.5 hours are speech. This paper describes the corpus and presents benchmark results for the tasks of speech recognition, speech syn…
In this work, we present a novel audio-visual dataset for active speaker detection in the wild. A speaker is considered active when his or her face is visible and the voice is audible simultaneously. Although active speaker detection is a crucial pre-processing step for many audio-visual tasks, there is no existing dataset of natural human speech to evaluate the performance of active speaker detection. We therefore curate the Active Speakers in the Wild (ASW) dataset which contains videos and co-occurring speech segments with dense speech activity labels. Videos and timestamps of audible segme…
This paper proposes a new strategy for learning powerful cross-modal embeddings for audio-to-video synchronization. Here, we set up the problem as one of cross-modal retrieval, where the objective is to find the most relevant audio segment given a short video clip. The method builds on the recent advances in learning representations from cross-modal self-supervision. The main contributions of this paper are as follows: (1) we propose a new learning strategy where the embeddings are learnt via a multi-way matching problem, as opposed to a binary classification (matching or non-matching) problem…
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…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）
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 seg…
École de Technologie Supérieure, University of Québec（魁北克大学高等技术学院）
This paper presents a novel deep neural network (DNN) for multimodal fusion of audio, video and text modalities for emotion recognition. The proposed DNN architecture has independent and shared layers which aim to learn the representation for each modality, as well as the best combined representation to achieve the best prediction. Experimental results on the AVEC Sentiment Analysis in the Wild dataset indicate that the proposed DNN can achieve a higher level of Concordance Correlation Coefficient (CCC) than other state-of-the-art systems that perform early fusion of modalities at feature-leve…
Beijing Seek Truth Data Technology Co.,Ltd.（北京求真数据科技有限公司）；Renmin University of China（中国人民大学）；Ant Group（蚂蚁集团）
In this paper, we briefly introduce our submission to the Valence-Arousal Estimation Challenge of the 3rd Affective Behavior Analysis in-the-wild (ABAW) competition. Our method utilizes the multi-modal information, i.e., the visual and audio information, and employs a temporal encoder to model the temporal context in the videos. Besides, a smooth processor is applied to get more reasonable predictions, and a model ensemble strategy is used to improve the performance of our proposed method. The experiment results show that our method achieves 65.55% ccc for valence and 70.88% ccc for arousal on…
We introduce an approach to convert mono audio recorded by a 360 video camera into spatial audio, a representation of the distribution of sound over the full viewing sphere. Spatial audio is an important component of immersive 360 video viewing, but spatial audio microphones are still rare in current 360 video production. Our system consists of end-to-end trainable neural networks that separate individual sound sources and localize them on the viewing sphere, conditioned on multi-modal analysis of audio and 360 video frames. We introduce several datasets, including one filmed ourselves, and on…
University of Oxford（牛津大学）；Google DeepMind（谷歌DeepMind）
The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is compl…
Imperial College London（帝国理工学院）；University College London（伦敦大学学院）；University of Augsburg（奥格斯堡大学）；University of Oulu（奥卢大学）
Synthesising 3D facial motion from speech is a crucial problem manifesting in a multitude of applications such as computer games and movies. Recently proposed methods tackle this problem in controlled conditions of speech. In this paper, we introduce the first methodology for 3D facial motion synthesis from speech captured in arbitrary recording conditions ("in-the-wild") and independent of the speaker. For our purposes, we captured 4D sequences of people uttering 500 words, contained in the Lip Reading Words (LRW) a publicly available large-scale in-the-wild dataset, and built a set of 3D ble…
Sony Group Corporation（索尼集团公司）；University of California San Diego（加州大学圣地亚哥分校）
Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled env…
Austria Institute of Technology（奥地利技术研究院）；University of Essex（埃塞克斯大学）；FPT University（FPT大学）；FPT Software Company Limited（FPT软件有限公司）
This paper presents a task of audio-visual scene classification (SC) where input videos are classified into one of five real-life crowded scenes: 'Riot', 'Noise-Street', 'Firework-Event', 'Music-Event', and 'Sport-Atmosphere'. To this end, we firstly collect an audio-visual dataset (videos) of these five crowded contexts from Youtube (in-the-wild scenes). Then, a wide range of deep learning frameworks are proposed to deploy either audio or visual input data independently. Finally, results obtained from high-performed deep learning frameworks are fused to achieve the best accuracy score. Our ex…
China Pacific Insurance (Group) Co., Ltd.（中国太平洋保险（集团）股份有限公司）；Shanghai Jiaotong University（上海交通大学）
Analyzing human affect is vital for human-computer interaction systems. Most methods are developed in restricted scenarios which are not practical for in-the-wild settings. The Affective Behavior Analysis in-the-wild (ABAW) 2021 Contest provides a benchmark for this in-the-wild problem. In this paper, we introduce a multi-modal and multi-task learning method by using both visual and audio information. We use both AU and expression annotations to train the model and apply a sequence model to further extract associations between video frames. We achieve an AU score of 0.712 and an expression sco…
The goal of this work is to synchronise audio and video of a talking face using deep neural network models. Existing works have trained networks on proxy tasks such as cross-modal similarity learning, and then computed similarities between audio and video frames using a sliding window approach. While these methods demonstrate satisfactory performance, the networks are not trained directly on the task. To this end, we propose an end-to-end trained network that can directly predict the offset between an audio stream and the corresponding video stream. The similarity matrix between the two modali…
This paper presents a novel CNN-RNN based approach, which exploits multiple CNN features for dimensional emotion recognition in-the-wild, utilizing the One-Minute Gradual-Emotion (OMG-Emotion) dataset. Our approach includes first pre-training with the relevant and large in size, Aff-Wild and Aff-Wild2 emotion databases. Low-, mid- and high-level features are extracted from the trained CNN component and are exploited by RNN subnets in a multi-task framework. Their outputs constitute an intermediate level prediction; final estimates are obtained as the mean or median values of these predictions.…
Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（人工智能研究院）；University of Maryland（马里兰大学）；Chung-Ang University（Chung-Ang 大学）；Georgetown University（乔治城大学）；Miraflow AI
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…
The Chinese University of Hong Kong（香港中文大学）；Zhejiang University（浙江大学）；Shanghai Jiao Tong University（上海交通大学）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；S-Lab, Nanyang Technological University（南洋理工大学S-Lab）
The task of audio-visual sound source localization has been well studied under constrained scenes, where the audio recordings are clean. However, in real-world scenarios, audios are usually contaminated by off-screen sound and background noise. They will interfere with the procedure of identifying desired sources and building visual-sound connections, making previous studies non-applicable. In this work, we propose the Interference Eraser (IEr) framework, which tackles the problem of audio-visual sound source localization in the wild. The key idea is to eliminate the interference by redefining…
University of Delaware（特拉华大学）；Target Corporation（塔吉特公司）
This paper presents an audiovisual-based emotion recognition hybrid network. While most of the previous work focuses either on using deep models or hand-engineered features extracted from images, we explore multiple deep models built on both images and audio signals. Specifically, in addition to convolutional neural networks (CNN) and recurrent neutral networks (RNN) trained on facial images, the hybrid network also contains one SVM classifier trained on holistic acoustic feature vectors, one long short-term memory network (LSTM) trained on short-term feature sequences extracted from segmented…
Technical University of Munich（慕尼黑工业大学）；Microsoft Corporation（微软公司）
Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, whi…
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method based on the temporal correlation between audio and video streams. The main idea is that the correlation between audio and video in adversarial examples will be lower than benign examples due to added adversarial noise. We use the synchronisation confidence score as a proxy for audiovisual correlation and based on it we can detect adversarial attacks. To th…
CSTR, School of Informatics, University of Edinburgh, UK（英国爱丁堡大学信息学院语音技术研究中心）
Audiovisual synchronisation is the task of determining the time offset between speech audio and a video recording of the articulators. In child speech therapy, audio and ultrasound videos of the tongue are captured using instruments which rely on hardware to synchronise the two modalities at recording time. Hardware synchronisation can fail in practice, and no mechanism exists to synchronise the signals post hoc. To address this problem, we employ a two-stream neural network which exploits the correlation between the two modalities to find the offset. We train our model on recordings from 69 s…
Xidian University（西安电子科技大学）；Tencent AI Lab（腾讯人工智能实验室）；Tsinghua University（清华大学）
We present VideoReTalking, a new system to edit the faces of a real-world talking head video according to input audio, producing a high-quality and lip-syncing output video even with a different emotion. Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism. Given a talking-head video, we first modify the expression of each frame according to the same expression template using the expression editing network, resulting in a video with the canonical…
Indian Institute of Technology Ropar（印度理工学院罗巴尔分校）；University of Canberra（堪培拉大学）；Australian National University（澳大利亚国立大学）
This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge. EmotiW 2018 is a grand challenge in the ACM International Conference on Multimodal Interaction 2018, Colorado, USA. The challenge aims at providing a common platform to researchers working in the affective computing community to benchmark their algorithms on `in the wild' data. This year EmotiW contains three sub-challenges: a) Audio-video based emotion recognition; b) Student engagement prediction; and c) Group-level emotion recognition. The databases, protocols and baselines are discussed in detail.
Talking face generation with great practical significance has attracted more attention in recent audio-visual studies. How to achieve accurate lip synchronization is a long-standing challenge to be further investigated. Motivated by xxx, in this paper, an AttnWav2Lip model is proposed by incorporating spatial attention module and channel attention module into lip-syncing strategy. Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction. To our limited knowledge, this is the first attempt to…
The task of recognizing human facial expressions plays a vital role in various human-related systems, including health care and medical fields. With the recent success of deep learning and the accessibility of a large amount of annotated data, facial expression recognition research has been mature enough to be utilized in real-world scenarios with audio-visual datasets. In this paper, we introduce Swin transformer-based facial expression approach for an in-the-wild audio-visual dataset of the Aff-Wild2 Expression dataset. Specifically, we employ a three-stream network (i.e., Visual stream, Tem…
Google Research（谷歌研究院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We introduce AudioScopeV2, a state-of-the-art universal audio-visual on-screen sound separation system which is capable of learning to separate sounds and associate them with on-screen objects by looking at in-the-wild videos. We identify several limitations of previous work on audio-visual on-screen sound separation, including the coarse resolution of spatio-temporal attention, poor convergence of the audio separation model, limited variety in training and evaluation data, and failure to account for the trade off between preservation of on-screen sounds and suppression of off-screen sounds. W…
Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are increasingly becoming an indispensable part of our life. Accurately annotated real-world data are the crux in devising such systems. However, existing databases usually consider controlled settings, low demographic variability, and a single task. In this paper, we introduce the SEWA database of more than 2000 minutes of audio-visual data of 398 people coming from six cultures, 50% female, and uniformly spanning …
Visual speech recognition (VSR) aims to recognize the content of speech based on lip movements, without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to the larger training sets rather than the model design. Here we demonstrate that designing better models is equally as important as using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model, and highlight the imp…
University of Oxford（牛津大学）；Omilia Conversational Intelligence（奥米利亚对话智能公司）
The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio. We propose a zero-shot method suitable for in the wild videos. Our key contributions are: (1) a novel convolutional architecture, KWS-Net, that uses a similarity map intermediate representation to separate the task into (i) sequence matching, and (ii) pattern detection, to decide whether the word is there and when; (2) we demonstrate that if audio is available, visual keyword spotting improves the performance both for a clean and noisy audio signal. Fi…
