Most audio processing pipelines involve transformations that act on fixed-dimensional input representations of audio. For example, when using the Short Time Fourier Transform (STFT) the DFT size specifies a fixed dimension for the input representation. As a consequence, most audio machine learning models are designed to process fixed-size vector inputs which often prohibits the repurposing of learned models on audio with different sampling rates or alternative representations. We note, however, that the intrinsic spectral information in the audio signal is invariant to the choice of the input representation or the sampling rate. Motivated by this, we introduce a novel way of processing audio signals by treating them as a collection of points in feature space, and we use point cloud machine learning models that give us invariance to the choice of representation parameters, such as DFT size or the sampling rate. Additionally, we observe that these methods result in smaller models, and allow us to significantly subsample the input representation with minimal effects to a trained model performance.
National and Kapodistrian University of Athens（雅典国立卡波迪斯特里安大学）；University of Piraeus（比雷埃夫斯大学）
We apply post-processing to the class probability distribution outputs of audio event classification models and employ reinforcement learning to jointly discover the optimal parameters for various stages of a post-processing stack, such as the classification thresholds and the kernel sizes of median filtering algorithms used to smooth out model predictions. To achieve this we define a reinforcement learning environment where: 1) a state is the class probability distribution provided by the model for a given audio sample, 2) an action is the choice of a candidate optimal value for each paramete…
University of Electronic Science and Technology of China（电子科技大学）
With the development of deep learning and artificial intelligence, audio synthesis has a pivotal role in the area of machine learning and shows strong applicability in the industry. Meanwhile, significant efforts have been dedicated by researchers to handle multimodal tasks at present such as audio-visual multimodal processing. In this paper, we conduct a survey on audio synthesis and audio-visual multimodal processing, which helps understand current research and future trends. This review focuses on text to speech(TTS), music generation and some tasks that combine visual and acoustic informat…
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.
University of Augsburg（奥格斯堡大学）；Imperial College London（帝国理工学院）
Deep neural speech and audio processing systems have a large number of trainable parameters, a relatively complex architecture, and require a vast amount of training data and computational power. These constraints make it more challenging to integrate such systems into embedded devices and utilise them for real-time, real-world applications. We tackle these limitations by introducing DeepSpectrumLite, an open-source, lightweight transfer learning framework for on-device speech and audio recognition using pre-trained image convolutional neural networks (CNNs). The framework creates and augments…
Digital audio processing tools offer music researchers the opportunity to examine both non-notated music and music as performance. This chapter summarises the types of information that can be extracted from audio as well as currently available audio tools for music corpus studies. The survey of extraction methods includes both a primer on signal processing and background theory on audio feature extraction. The survey of audio tools focuses on widely used tools, including both those with a graphical user interface, namely Audacity and Sonic Visualiser, and code-based tools written in the C/C++,…
The system we used for Task 6 (Automated Audio Captioning)of the Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge combines three elements, namely, dataaugmentation, multi-task learning, and post-processing, for audiocaptioning. The system received the highest evaluation scores, butwhich of the individual elements most fully contributed to its perfor-mance has not yet been clarified. Here, to asses their contributions,we first conducted an element-wise ablation study on our systemto estimate to what extent each element is effective. We then con-ducted a detailed …
University of Augsburg（奥格斯堡大学）；TCS Research（塔塔咨询服务研究院）；Imperial College London（帝国理工学院）
The Coronavirus (COVID-19) pandemic has been the research focus world-wide in the year 2020. Several efforts, from collection of COVID-19 patients' data to screening them for the virus's detection are taken with rigour. A major portion of COVID-19 symptoms are related to the functioning of the respiratory system, which in-turn critically influences the human speech production system. This drives the research focus towards identifying the markers of COVID-19 in speech and other human generated audio signals. In this paper, we give an overview of the speech and other audio signal, language and g…
University of Washington（华盛顿大学）；Microsoft AI and Research（微软人工智能与研究）
While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of neural networks on the performance of two common audio processing tasks, namely, voice-activity detection and single-channel speech enhancement. We determine the optimal pair of weight/neuron bit precision by exploring its impact on both the performance and processing time. Through experiments conducted with real user data, we demonstrate that deep neural net…
We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network. We then train a deep encoder to analyze input audio and control effect parameters to perform the desired signal manipulation, requiring only input-target paired audio data as supervision. To train our network with non-differentiable black-box effects layers, we use a fast, parallel stochastic gradient approximation scheme within a standard auto differentiation graph, yielding efficient end-to-end backpropagation. We demonstrate the p…
University of Edinburgh（爱丁堡大学）；Edinburgh Napier University（爱丁堡龙比亚大学）；University of Wolverhampton（伍尔弗汉普顿大学）
In this paper, we design a first of its kind transceiver (PHY layer) prototype for cloud-based audio-visual (AV) speech enhancement (SE) complying with high data rate and low latency requirements of future multimodal hearing assistive technology. The innovative design needs to meet multiple challenging constraints including up/down link communications, delay of transmission and signal processing, and real-time AV SE models processing. The transceiver includes device detection, frame detection, frequency offset estimation, and channel estimation capabilities. We develop both uplink (hearing aid…
Queen Mary University of London（伦敦玛丽女王大学）；Adobe Research（Adobe研究院）
We present a framework that can impose the audio effects and production style from one recording to another by example with the goal of simplifying the audio production process. We train a deep neural network to analyze an input recording and a style reference recording, and predict the control parameters of audio effects used to render the output. In contrast to past work, we integrate audio effects as differentiable operators in our framework, perform backpropagation through audio effects, and optimize end-to-end using an audio-domain loss. We use a self-supervised training strategy enabling…
Aalborg University Copenhagen（奥尔堡大学哥本哈根分校）；Google（谷歌）；Tampere University（坦佩雷大学）；CNRS LIS, Université de Toulon（土伦大学CNRS LIS实验室）；Austrian Research Institute for Artificial Intelligence（奥地利人工智能研究所）
Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variant…
With increasing amounts of music being digitally transferred from production to distribution, automatic means of determining media quality are needed. Protection mechanisms in digital audio processing tools have not eliminated the need of production entities located downstream the distribution chain to assess audio quality and detect defects inserted further upstream. Such analysis often relies on the received audio and scarce meta-data alone. Deliberate use of artefacts such as clicks in popular music as well as more recent defects stemming from corruption in modern audio encodings call for d…
Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
National University of Singapore（新加坡国立大学）；ASUS Intelligent Cloud Services（华硕智能云服务）；I2R, Agency for Science, Technology, and Research (A*STAR)（新加坡科技研究局信息研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Universidad Politécnica de Madrid（马德里理工大学）
Recently, significant progress has been made in audio source separation by the application of deep learning techniques. Current methods that combine both audio and visual information use 2D representations such as images to guide the separation process. However, in order to (re)-create acoustically correct scenes for 3D virtual/augmented reality applications from recordings of real music ensembles, detailed information about each sound source in the 3D environment is required. This demand, together with the proliferation of 3D visual acquisition systems like LiDAR or rgb-depth cameras, stimula…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We present pyroomacoustics, a software package aimed at the rapid development and testing of audio array processing algorithms. The content of the package can be divided into three main components: an intuitive Python object-oriented interface to quickly construct different simulation scenarios involving multiple sound sources and microphones in 2D and 3D rooms; a fast C implementation of the image source model for general polyhedral rooms to efficiently generate room impulse responses and simulate the propagation between sources and receivers; and finally, reference implementations of popular…
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…
Binghamton University, State University of New York（纽约州立大学宾汉姆顿大学）；Center for Collective Dynamics of Complex Systems（复杂系统集体动力学中心）；Department of Systems Science and Industrial Engineering（系统科学与工业工程系）；Bernard M. & Ruth R. Bass Center for Leadership Studies（伯纳德·M与露丝·R·巴斯领导力研究中心）
Utterance clustering is one of the actively researched topics in audio signal processing and machine learning. This study aims to improve the performance of utterance clustering by processing multichannel (stereo) audio signals. Processed audio signals were generated by combining left- and right-channel audio signals in a few different ways and then extracted embedded features (also called d-vectors) from those processed audio signals. This study applied the Gaussian mixture model for supervised utterance clustering. In the training phase, a parameter sharing Gaussian mixture model was conduct…
Low-rankness of amplitude spectrograms has been effectively utilized in audio signal processing methods including non-negative matrix factorization. However, such methods have a fundamental limitation owing to their amplitude-only treatment where the phase of the observed signal is utilized for resynthesizing the estimated signal. In order to address this limitation, we directly treat a complex-valued spectrogram and show a complex-valued spectrogram of a sum of sinusoids can be approximately low-rank by modifying its phase. For evaluating the applicability of the proposed low-rank representat…
Comparative Analysis of Mel-Frequency Cepstral Coefficients and Wavelet Based Audio Signal Processing for Emotion Detection and Mental Health Assessment in Spoken Speech
This document describes version 0.10 of TorchAudio: building blocks for machine learning applications in the audio and speech processing domain. The objective of TorchAudio is to accelerate the development and deployment of machine learning applications for researchers and engineers by providing off-the-shelf building blocks. The building blocks are designed to be GPU-compatible, automatically differentiable, and production-ready. TorchAudio can be easily installed from Python Package Index repository and the source code is publicly available under a BSD-2-Clause License (as of September 2021)…
Belmont University（贝尔蒙特大学）；ARiA Acoustics（ARiA声学公司）；Fraunhofer Institute for Digital Media Technology（弗劳恩霍夫数字媒体技术研究所）
In this work we present a data-driven approach for predicting the behavior of (i.e., profiling) a given non-linear audio signal processing effect (henceforth "audio effect"). Our objective is to learn a mapping function that maps the unprocessed audio to the processed by the audio effect to be profiled, using time-domain samples. To that aim, we employ a deep auto-encoder model that is conditioned on both time-domain samples and the control parameters of the target audio effect. As a test-case study, we focus on the offline profiling of two dynamic range compression audio effects, one software…
The L3DAS21 Challenge is aimed at encouraging and fostering collaborative research on machine learning for 3D audio signal processing, with particular focus on 3D speech enhancement (SE) and 3D sound localization and detection (SELD). Alongside with the challenge, we release the L3DAS21 dataset, a 65 hours 3D audio corpus, accompanied with a Python API that facilitates the data usage and results submission stage. Usually, machine learning approaches to 3D audio tasks are based on single-perspective Ambisonics recordings or on arrays of single-capsule microphones. We propose, instead, a novel m…
Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a performance penalty when trained on Fourier-based features. In this work, we introduce an architecture, Audiomer, where we combine 1D Residual Networks with Performer Attention to achieve state-of-the-art performance in keyword spotting with raw audio waveforms, outperforming all previous methods while being computationally cheaper and parameter-efficient. Addition…
Since the evolution of digital computers, the storage of data has always been in terms of discrete bits that can store values of either 1 or 0. Hence, all computer programs (such as MATLAB), convert any input continuous signal into a discrete dataset. Applying this to oscillating signals, such as audio, opens a domain for processing as well as editing. The Fourier transform, which is an integral over infinite limits, for the use of signal processing is discrete. The essential feature of the Fourier transform is to decompose any signal into a combination of multiple sinusoidal waves that are ea…
Spoken content processing (such as retrieval and browsing) is maturing, but the singing content is still almost completely left out. Songs are human voice carrying plenty of semantic information just as speech, and may be considered as a special type of speech with highly flexible prosody. The various problems in song audio, for example the significantly changing phone duration over highly flexible pitch contours, make the recognition of lyrics from song audio much more difficult. This paper reports an initial attempt towards this goal. We collected music-removed version of English songs direc…
We present the Geometric-Wave Acoustic (GWA) dataset, a large-scale audio dataset of about 2 million synthetic room impulse responses (IRs) and their corresponding detailed geometric and simulation configurations. Our dataset samples acoustic environments from over 6.8K high-quality diverse and professionally designed houses represented as semantically labeled 3D meshes. We also present a novel real-world acoustic materials assignment scheme based on semantic matching that uses a sentence transformer model. We compute high-quality impulse responses corresponding to accurate low-frequency and h…
Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
The University of New South Wales, Sydney, Australia（新南威尔士大学）；Tongyi Speech Lab, Alibaba Group, China（通义语音实验室）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）人工智能学院）
Corti（Corti 公司）；Technical University of Denmark（丹麦技术大学）
End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-ba…
The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction
University of Science and Technology of China（中国科学技术大学）；Georgia Institute of Technology（佐治亚理工学院）；Northwestern Polytechnical University（西北工业大学）；Carnegie Mellon University（卡内基梅隆大学）；Kore University of Enna（恩纳科雷大学）；Delft University of Technology（代尔夫特理工大学）；iFlytek（科大讯飞）
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems, detecting the presence of adversarial examples is of high practical relevance. By applying anomalous pattern detection techniques in the activation space of these models, we show that 2 of the recent and current state-of-the-art adversarial attacks on audio processing systems systematically lead to higher-than-expected activation at some subset of nodes and we…
TCS Research India（塔塔咨询服务公司印度研究院）；University of Augsburg（奥格斯堡大学）；Imperial College London（帝国理工学院）
Recently, there has been an increased attention towards innovating, enhancing, building, and deploying applications of speech signal processing for providing assistance and relief to human mankind from the Coronavirus (COVID-19) pandemic. Many AI with speech initiatives are taken to combat with the present situation and also to create a safe and secure environment for the future. This paper summarises all these efforts taken by the re-search community towards helping the individuals and the society in the fight against COVID-19 over the past 3-4 months using speech signal processing. We also s…
Processing of speech and audio signals with time-frequency representations require windowing methods which allow perfect reconstruction of the original signal and where processing artifacts have a predictable behavior. The most common approach for this purpose is overlap-add windowing, where signal segments are windowed before and after processing. Commonly used windows include the half-sine and a Kaiser-Bessel derived window. The latter is an approximation of the discrete prolate spherical sequence, and thus a maximum energy concentration window, adapted for overlap-add. We demonstrate that p…
Reverse the auditory processing pathway: Coarse-to-fine audio reconstruction from fMRI
Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology（脑认知与类脑智能技术重点实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）
Audio production techniques which previously only existed in GUI-constrained digital audio workstations, livecoding environments, or C++ APIs are now accessible with our new Python module called DawDreamer. DawDreamer therefore bridges the gap between real sound engineers and coders imitating them with offline batch-processing. Like contemporary modules in this domain, DawDreamer can create directed acyclic graphs of audio processors such as VSTs which generate or manipulate audio streams. DawDreamer can also dynamically compile and execute code from Faust, a powerful signal processing languag…
University of Augsburg（奥格斯堡大学）；Johannes Kepler University Linz（约翰内斯·开普勒大学林茨分校）；Beijing Institute of Technology（北京理工大学）；Imperial College London（帝国理工学院）
Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task. Its success in the fields of computer vision and natural language processing have prompted its recent adoption into the field of audio and speech processing. Comprehensive reviews summarising the knowledge in audio SSL are currently missing. To fill this gap, in the present work, we provide an overview of the SSL methods used for audio …
Sound event detection (SED) aims at identifying audio events (audio tagging task) in recordings and then locating them temporally (localization task). This last task ends with the segmentation of the frame-level class predictions, that determines the onsets and offsets of the audio events. Yet, this step is often overlooked in scientific publications. In this paper, we focus on the post-processing algorithms used to identify the audio event boundaries. Different post-processing steps are investigated, through smoothing, thresholding, and optimization. In particular, we evaluate different appro…
