Deep audio classification, traditionally cast as training a deep neural network on top of mel-filterbanks in a supervised fashion, has recently benefited from two independent lines of work. The first one explores "learnable frontends", i.e., neural modules that produce a learnable time-frequency representation, to overcome limitations of fixed features. The second one uses self-supervised learning to leverage unprecedented scales of pre-training data. In this work, we study the feasibility of combining both approaches, i.e., pre-training learnable frontend jointly with the main architecture for downstream classification. First, we show that pretraining two previously proposed frontends (SincNet and LEAF) on Audioset drastically improves linear-probe performance over fixed mel-filterbanks, suggesting that learnable time-frequency representations can benefit self-supervised pre-training even more than supervised training. Surprisingly, randomly initialized learnable filterbanks outperform mel-scaled initialization in the self-supervised setting, a counter-intuitive result that questions the appropriateness of strong priors when designing learnable filters. Through exploratory analysis of the learned frontend components, we uncover crucial differences in properties of these frontends when used in a supervised and self-supervised setting, especially the affinity of self-supervised filters to diverge significantly from the mel-scale to model a broader range of frequencies.
Imperial College London（帝国理工学院）；Samsung AI Centre, Cambridge（三星人工智能中心（剑桥））；Facebook London（Facebook（伦敦））
The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au…
Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual modalities for cross-modal self-supervision. This work (1) investigates visual self-supervision via face reconstruction to guide the learning of audio representations; (2) proposes an audio-only self-supervision approach for speech representation learning; (3) shows that a multi-task combination of the proposed visual and audio self-supervision is beneficial for …
Imperial College London（伦敦帝国理工学院）；Facebook London（脸书伦敦）；University of Augsburg（奥格斯堡大学）
The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac…
While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the label efficiency of large neural networks operating on audio data through a combination of multitask learning and self-supervised learning on unlabeled data. We trained an end-to-end audio feature extractor based on WaveNet that feeds into simple, yet versatile task-specific neural networks. We describe several easily implemented self-supervised learning tasks…
In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning is to map an audio signal and its various augmented versions (representative of salient aspects of audio like pitch, timbre etc.) to a space where they are close together, and are separated from other different signals. In addition we also explore generative models based on state of the art transformer based architectures for learning latent spaces for audio signals, without acc…
Inspired by the recent progress in self-supervised learning for computer vision that generates supervision using data augmentations, we explore a new general-purpose audio representation learning approach. We propose learning general-purpose audio representation from a single audio segment without expecting relationships between different time segments of audio samples. To implement this principle, we introduce Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced "viola"), an audio self-supervised learning method based on BYOL for learning general-purpose audio representation. Unlike…
Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular choice for self-supervision in the audio domain, and typically provide a learning signal by forcing the model to be invariant to some transformations of the input. These methods, however, require measures such as negative sampling or some form of regularisation to be taken to prevent the model from collapsing on trivial solutions. In this work, instead of invari…
Seoul National University（首尔国立大学）；SK Telecom（SK电讯）
Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original aud…
University of Warwick（华威大学）；Google Research（谷歌研究院）；University of Glasgow（格拉斯哥大学）
Large scale databases with high-quality manual annotations are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a graph node, we propose a subgraph-based framework with novel self-supervision tasks that can learn effective audio representations. During training, subgraphs are constructed by sampling the entire pool of available training data to exploit the relationship between the labelled and unlabeled audio samples. During inference, we use random edges to alleviate t…
University of Southern Queensland（南昆士兰大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Recent improvements in Generative Adversarial Neural Networks (GANs) have shown their ability to generate higher quality samples as well as to learn good representations for transfer learning. Most of the representation learning methods based on GANs learn representations ignoring their post-use scenario, which can lead to increased generalisation ability. However, the model can become redundant if it is intended for a specific task. For example, assume we have a vast unlabelled audio dataset, and we want to learn a representation from this dataset so that it can be used to improve the emotion…
Weakly supervised learning algorithms are critical for scaling audio event detection to several hundreds of sound categories. Such learning models should not only disambiguate sound events efficiently with minimal class-specific annotation but also be robust to label noise, which is more apparent with weak labels instead of strong annotations. In this work, we propose a new framework for designing learning models with weak supervision by bridging ideas from sequential learning and knowledge distillation. We refer to the proposed methodology as SeCoST (pronounced Sequest) -- Sequential Co-super…
Mainstream Audio Analytics models are trained to learn under the paradigm of one class label to many recordings focusing on one task. Learning under such restricted supervision limits the flexibility of models because they require labeled audio for training and can only predict the predefined categories. Instead, we propose to learn audio concepts from natural language supervision. We call our approach Contrastive Language-Audio Pretraining (CLAP), which learns to connect language and audio by using two encoders and a contrastive learning to bring audio and text descriptions into a joint multi…
In this paper, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non-negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a so…
Robust Audio Tagging under Class-wise Supervision Unreliability
Machine Learning Research Group, Engineering Science, University of Oxford（牛津大学机器学习研究组）；GISP, Harbin Engineering University（哈尔滨工程大学GISP）；EECS, KTH Royal Institute of Technology（皇家理工学院电子工程与计算机科学系）；CVSSP, University of Surrey（萨里大学计算机视觉与模式识别实验室）
Music Technology Group, Universitat Pompeu Fabra（庞培法布拉大学音乐技术组）；Google, Inc.（谷歌公司）
This paper introduces Task 2 of the DCASE2019 Challenge, titled "Audio tagging with noisy labels and minimal supervision". This task was hosted on the Kaggle platform as "Freesound Audio Tagging 2019". The task evaluates systems for multi-label audio tagging using a large set of noisy-labeled data, and a much smaller set of manually-labeled data, under a large vocabulary setting of 80 everyday sound classes. In addition, the proposed dataset poses an acoustic mismatch problem between the noisy train set and the test set due to the fact that they come from different web audio sources. This can …
The lack of annotated training data in bioacoustics hinders the use of large-scale neural network models trained in a supervised way. In order to leverage a large amount of unannotated audio data, we propose AVES (Animal Vocalization Encoder based on Self-Supervision), a self-supervised, transformer-based audio representation model for encoding animal vocalizations. We pretrain AVES on a diverse set of unannotated audio datasets and fine-tune them for downstream bioacoustics tasks. Comprehensive experiments with a suite of classification and detection tasks have shown that AVES outperforms all…
Queen Mary University of London（伦敦玛丽女王大学）；Universal Music Group（环球音乐集团）
Audio representations for music information retrieval are typically learned via supervised learning in a task-specific fashion. Although effective at producing state-of-the-art results, this scheme lacks flexibility with respect to the range of applications a model can have and requires extensively annotated datasets. In this work, we pose the question of whether it may be possible to exploit weakly aligned text as the only supervisory signal to learn general-purpose music audio representations. To address this question, we design a multimodal architecture for music and language pre-training (…
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…
MATS: An Audio Language Model under Text-only Supervision
Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, China（中国科学院智能信息处理重点实验室（中国科学院））；University of Chinese Academy of Sciences, China（中国科学院大学）
We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-super…
FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining
X-LANCE Lab, Shanghai Jiao Tong University（上海交通大学X-LANCE实验室）；SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University（上海交通大学巴黎卓越工程师学院）；Shanghai Innovation Institute（上海创新研究院）；The Chinese University of Hong Kong（香港中文大学）
Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual labeling cost. This work proposes pseudo strong labels (PSL), a simple label augmentation framework that enhances the supervision quality for large-scale weakly supervised audio tagging. A machine annotator is first trained on a large weakly supervised dataset, which then provides finer supervision for a student model. Using PSL we achieve an mAP of 35.95 balanced train subset of Audioset using a MobileNetV2 back-end, sig…
Recent studies in singing voice synthesis have achieved high-quality results leveraging advances in text-to-speech models based on deep neural networks. One of the main issues in training singing voice synthesis models is that they require melody and lyric labels to be temporally aligned with audio data. The temporal alignment is a time-exhausting manual work in preparing for the training data. To address the issue, we propose a melody-unsupervision model that requires only audio-and-lyrics pairs without temporal alignment in training time but generates singing voice audio given a melody and l…
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the objective nature of the loss function usually leads to suboptimal sound quality as well as high run-time complexity due to the large model size. In this work, we present a psychoacoustic calibration scheme to re-define the loss functions of neural audio coding systems so that it can decode signals more perceptually similar to the reference, yet with a much lower m…
The Cooper Union for the Advancement of Science and Art（库珀高等科学艺术联盟学院）
A method for musical audio synthesis using autoencoding neural networks is proposed. The autoencoder is trained to compress and reconstruct magnitude short-time Fourier transform frames. The autoencoder produces a spectrogram by activating its smallest hidden layer, and a phase response is calculated using real-time phase gradient heap integration. Taking an inverse short-time Fourier transform produces the audio signal. Our algorithm is light-weight when compared to current state-of-the-art audio-producing machine learning algorithms. We outline our design process, produce metrics, and detail…
We propose the Neuralogram -- a deep neural network based representation for understanding audio signals which, as the name suggests, transforms an audio signal to a dense, compact representation based upon embeddings learned via a neural architecture. Through a series of probing signals, we show how our representation can encapsulate pitch, timbre and rhythm-based information, and other attributes. This representation suggests a method for revealing meaningful relationships in arbitrarily long audio signals that are not readily represented by existing algorithms. This has the potential for nu…
We measure the effect of small amounts of systematic and random label noise caused by slightly misaligned ground truth labels in a fine grained audio signal labeling task. The task we choose to demonstrate these effects on is also known as framewise polyphonic transcription or note quantized multi-f0 estimation, and transforms a monaural audio signal into a sequence of note indicator labels. It will be shown that even slight misalignments have clearly apparent effects, demonstrating a great sensitivity of convolutional neural networks to label noise. The implications are clear: when using conv…
University of Padua（帕多瓦大学）；Missouri State University（密苏里州立大学）；Tampere University（坦佩雷大学）
In this paper, ensembles of classifiers that exploit several data augmentation techniques and four signal representations for training Convolutional Neural Networks (CNNs) for audio classification are presented and tested on three freely available audio classification datasets: i) bird calls, ii) cat sounds, and iii) the Environmental Sound Classification dataset. The best performing ensembles combining data augmentation techniques with different signal representations are compared and shown to outperform the best methods reported in the literature on these datasets. The approach proposed here…
Acoustics Research Institute, Austrian Academy of Sciences（奥地利科学院声学研究所）；Swiss Data Science Center, ETH Zürich（苏黎世联邦理工学院瑞士数据科学中心）
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps. The input to the DNN was the context, i.e., the signal surrounding the gap, transformed into time-frequency (TF) coefficients. Our results were compared to those obtained from a reference method based on linear predictive coding (LPC). For music, our …
A number of recent advances in neural audio synthesis rely on upsampling layers, which can introduce undesired artifacts. In computer vision, upsampling artifacts have been studied and are known as checkerboard artifacts (due to their characteristic visual pattern). However, their effect has been overlooked so far in audio processing. Here, we address this gap by studying this problem from the audio signal processing perspective. We first show that the main sources of upsampling artifacts are: (i) the tonal and filtering artifacts introduced by problematic upsampling operators, and (ii) the sp…
Queen Mary University of London（伦敦玛丽女王大学）；Institute for Research and Coordination in Acoustics/Music（声学/音乐研究与协调研究所）
The identification of structural differences between a music performance and the score is a challenging yet integral step of audio-to-score alignment, an important subtask of music information retrieval. We present a novel method to detect such differences between the score and performance for a given piece of music using progressively dilated convolutional neural networks. Our method incorporates varying dilation rates at different layers to capture both short-term and long-term context, and can be employed successfully in the presence of limited annotated data. We conduct experiments on audi…
University of Surrey（萨里大学）；Tencent AI Lab（腾讯人工智能实验室）；Qingdao University of Science and Technology（青岛科技大学）
Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We investigate audio tagging on AudioSet, which is a dataset consisting of over 2 million audio clips and 527 classes. AudioSet is weakly labelled, in that only the presence or absence of sound classes is known for each clip, while the onset and offset times are unknown. To address the weakly-labelled audio tagging problem, we propose attention neural networks as a way t…
Speaker clustering is the task of differentiating speakers in a recording. In a way, the aim is to answer "who spoke when" in audio recordings. A common method used in industry is feature extraction directly from the recording thanks to MFCC features, and by using well-known techniques such as Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM). In this paper, we studied neural networks (especially CNN) followed by clustering and audio processing in the quest to reach similar accuracy to state-of-the-art methods.
Applications of deep learning for audio effects often focus on modeling analog effects or learning to control effects to emulate a trained audio engineer. However, deep learning approaches also have the potential to expand creativity through neural audio effects that enable new sound transformations. While recent work demonstrated that neural networks with random weights produce compelling audio effects, control of these effects is limited and unintuitive. To address this, we introduce a method for the steerable discovery of neural audio effects. This method enables the design of effects using…
Northwestern University（西北大学）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）
While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitoring, it may not be possible to obtain isolated signals for training. Here, we propose objective functions and network architectures that enable training a source separation system with weak labels. In this scenario, weak labels are defined in contrast with strong time-frequency (T…
