The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performance improvements range between 7% and 30% depending on the noise level when leveraging the visual modality of speech in addition to the auditory one. This work presents a variant of AV Align where the recurrent Long Short-term Memory (LSTM) computation block is replaced by the more recently proposed Transformer block. We compare the two methods, discussing in greater detail their strengths and weaknesses. We find that Transformers also learn cross-modal monotonic alignments, but suffer from the same visual convergence problems as the LSTM model, calling for a deeper investigation into the dominant modality problem in machine learning.
University of Augsburg（奥格斯堡大学）；University of Nottingham（诺丁汉大学）
In this paper, we present our submission to 3rd Affective Behavior Analysis in-the-wild (ABAW) challenge. Learningcomplex interactions among multimodal sequences is critical to recognise dimensional affect from in-the-wild audiovisual data. Recurrence and attention are the two widely used sequence modelling mechanisms in the literature. To clearly understand the performance differences between recurrent and attention models in audiovisual affect recognition, we present a comprehensive evaluation of fusion models based on LSTM-RNNs, self-attention and cross-modal attention, trained for valence …
This paper presents a way of doing large scale audio understanding without traditional state of the art neural architectures. Ever since the introduction of deep learning for understanding audio signals in the past decade, convolutional architectures have been able to achieve state of the art results surpassing traditional hand-crafted features. In the recent past, there has been a similar shift away from traditional convolutional and recurrent neural networks towards purely end-to-end Transformer architectures. We, in this work, explore an approach, based on Bag-of-Words model. Our approach d…
We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text. Shallow neural networks map the embeddings to a common dimensionality. Our system, which is an extension of our submission to the Language-based Audio Retrieval Task of the DCASE Challenge 2022, employs the RoBERTa foundation model as the text embedding extractor. A pretrained PANNs model extracts the audio embeddings. To improve the generalisation of our mode…
We provide the technical report for Ego4D audio-only diarization challenge in ECCV 2022. Speaker diarization takes the audio streams as input and outputs the homogeneous segments according to the speaker's identity. It aims to solve the problem of "Who spoke when." In this paper, we explore a Detection-based method to tackle the audio-only speaker diarization task. Our method first extracts audio features by audio backbone and then feeds the feature to a detection-generate network to get the speaker proposals. Finally, after postprocessing, we can get the diarization results. The validation da…
Exploring bat song syllable representations in self-supervised audio encoders
Institute for Logic, Language and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）；Museum für Naturkunde, Leibniz Institute for Evolution and Biodiversity Science（莱布尼茨进化与生物多样性科学自然博物馆）
Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for deep feature understanding or model explanation focus on highlighting input data features that are relevant for classification decisions. In this work, we instead take the perspective of relating deep features to well-studied, hand-crafted features that are meaningful for the application of interest. We propose a methodology and set of systematic experiments for exploring deep features in this setting, where input f…
Deep neural networks have shown promise for music audio signal processing applications, often surpassing prior approaches, particularly as end-to-end models in the waveform domain. Yet results to date have tended to be constrained by low sample rates, noise, narrow domains of signal types, and/or lack of parameterized controls (i.e. "knobs"), making their suitability for professional audio engineering workflows still lacking. This work expands on prior research published on modeling nonlinear time-dependent signal processing effects associated with music production by means of a deep neural ne…
AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark
Fraunhofer Heinrich-Hertz-Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD——柏林学习与数据基础研究所）
University of Cambridge（剑桥大学）；University of Southampton（南安普顿大学）
Researchers have been battling with the question of how we can identify Coronavirus disease (COVID-19) cases efficiently, affordably and at scale. Recent work has shown how audio based approaches, which collect respiratory audio data (cough, breathing and voice) can be used for testing, however there is a lack of exploration of how biases and methodological decisions impact these tools' performance in practice. In this paper, we explore the realistic performance of audio-based digital testing of COVID-19. To investigate this, we collected a large crowdsourced respiratory audio dataset through …
The ability of deep neural networks to learn complex data relations and representations is established nowadays, but it generally relies on large sets of training data. This work explores a "piece-specific" autoencoding scheme, in which a low-dimensional autoencoder is trained to learn a latent/compressed representation specific to a given song, which can then be used to infer the song structure. Such a model does not rely on supervision nor annotations, which are well-known to be tedious to collect and often ambiguous in Music Structure Analysis. We report that the proposed unsupervised auto-…
Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechan…
Tianjin University（天津大学）；National Institute of Informatics（日本国立信息学研究所）
Audio-visual (AV) lip biometrics is a promising authentication technique that leverages the benefits of both the audio and visual modalities in speech communication. Previous works have demonstrated the usefulness of AV lip biometrics. However, the lack of a sizeable AV database hinders the exploration of deep-learning-based audio-visual lip biometrics. To address this problem, we compile a moderate-size database using existing public databases. Meanwhile, we establish the DeepLip AV lip biometrics system realized with a convolutional neural network (CNN) based video module, a time-delay neura…
University of Cambridge（剑桥大学）；University of Southampton（南安普顿大学）
Recent work has shown the potential of using audio data (eg, cough, breathing, and voice) in the screening for COVID-19. However, these approaches only focus on one-off detection and detect the infection given the current audio sample, but do not monitor disease progression in COVID-19. Limited exploration has been put forward to continuously monitor COVID-19 progression, especially recovery, through longitudinal audio data. Tracking disease progression characteristics could lead to more timely treatment. The primary objective of this study is to explore the potential of longitudinal audio sam…
Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation
Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing（人工智能研究院、深圳MSU-BIT大学及粤港澳大湾区情感智能与普适计算联合实验室）；School of Software Engineering, South China University of Technology（华南理工大学软件学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
Lincoln University（林肯大学）；Queen Mary University of London（伦敦玛丽女王大学）
We analyse multi-purpose audio using tools to visualise similarities within the data that may be observed via unsupervised methods. The success of machine learning classifiers is affected by the information contained within system inputs, so we investigate whether latent patterns within the data may explain performance limitations of such classifiers. We use the visual assessment of cluster tendency (VAT) technique on a well known data set to observe how the samples naturally cluster, and we make comparisons to the labels used for audio geotagging and acoustic scene classification. We demonstr…
Communication Science Laboratories, Nippon Telegraph and Telephone Corporation（日本电报电话公司通信科学实验室）
Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for general audio tasks should provide multiple aspects of robust features of the input sound. For recognizing sounds regardless of perturbations such as varying pitch or timbre, features should be robust to these perturbations. For serving the diverse needs of tasks such as recognition of emotions or music genres, representations should provide multiple aspects of information, such as local and global features. To implement …
In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech recognition tasks using a combination of in-domain data and almost 6 thousand hours of out-of-domain transcribed speech. We are presenting a large palette of experiments with various fine-tuning setups evaluated on two public datasets (CommonVoice and VoxPopuli) and one extremely challenging dataset from the MALACH project. Our results show that monolingual Wav2Vec 2…
Exploring Text-Queried Sound Event Detection with Audio Source Separation
School of Marine Science and Technology, Northwestern Polytechnical University（西北工业大学海洋科学与技术学院）；Alibaba Group（阿里巴巴集团）；Fortemedia Singapore（Fortemedia新加坡公司）
本文提出 TQ-SED 框架，通过预训练改进的 AudioSep-DP 语言查询音频源分离模型分离重叠事件，再由多分支检测目标声音，显著提升 SED 性能。
Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data
South China University of Technology（华南理工大学）；University of Georgia（佐治亚大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Massachusetts General Hospital（麻省总医院）
Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics
University of Technology Sydney（悉尼科技大学）；The University of Queensland（昆士兰大学）；Futureverse；The Hong Kong University of Science and Technology（香港科技大学）；CSIRO DATA61（联邦科学与工业研究组织数据61研究所）；Netease Fuxi AI Lab（网易伏羲人工智能实验室）
Institute for Advancing Intelligence, TCG Centres for Research and Education in Science and Technology（TCG科学与技术研究教育中心智能推进研究所）；Indian Statistical Institute, Kolkata（印度统计研究所）；Academy of Scientific and Innovative Research (AcSIR)（科学与创新研究院）
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology Beijing（北京科技大学）；Hong Kong Baptist University（香港浸会大学）；Microsoft（微软公司）；Chinese University of Hong Kong（香港中文大学）
针对现有音频 LLM 编解码器因压缩设计导致的语义缺陷问题，提出 X-Codec 方法，通过在 RVQ 前后融入语义特征与损失，显著降低语音合成 WER 并扩展至非语音任务，提升音频生成性能。
Exploring the User Experience of AI-Assisted Sound Searching Systems for Creative Workflows
Centre for Vision, Speech and Signal Processing, University of Surrey（视觉、语音和信号处理中心，萨里大学）；Research and Development, British Broadcasting Corporation（英国广播公司研发部）
Exploring the Potential of Data-Driven Spatial Audio Enhancement Using a Single-Channel Model
Faculdade de Engenharia Elétrica e de Computação（电气与计算工程学院）；Universidade Estadual de Campinas（坎皮纳斯州立大学）；Faculdade de Engenharia Acústica（声学工程学院）；Universidade Federal de Santa Maria（圣玛丽亚联邦大学）
Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation
School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Meituan（美团）
Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection
AudioCC Lab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（音频自监督实验室、计算机科学与工程系及人工智能关键实验室、人工智能研究院、上海交通大学）；Department of Electronic Engineering, Tsinghua University（电子工程系、清华大学）
We are exploring the design and implementation of artificial expressions, kinetic audio-visual representations of real-time physiological data that reflect emotional and cognitive state. In this work, we demonstrate a prototype, the Enactive Mandala, which maps real-time EEG signals to modulate ambient music and animated visual music. Transparent real-time audio-visual feedback of brainwave qualities supports intuitive insight into the connection between thoughts and physiological states.
