Unifying audio signal processing and machine learning: a fundamental framework for machine hearing

统一音频信号处理和机器学习：机器听力的基本框架

• 批准号: EP/L000776/1
• 负责人: Richard Turner
• 金额: $ 12.37万
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2013
• 资助国家: 英国
• 起止时间: 2013 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FL000776%2F1
• 关键词: Unifying; audio; signal; processing; machine

Modern technology is leading to a flood of audio data. For example, over seventy two hours of unstructured and unlabelled sound-tracks are uploaded to internet sites every minute. Automatic systems are urgently needed for recognising audio content so that these sound-tracks can be tagged for categorisation and search. Moreover, an increasing proportion of recordings are made on hand-held devices in challenging environments that contain multiple sound sources and noise. Such uncurated and noisy data necessitate automatic systems for cleaning the audio content and separating sources from mixtures. On a related note, devices for the hearing impaired currently perform poorly in noise. In fact, this is a major reason why six million people in the UK who would benefit from a hearing aid, do not use them (a market worth £18 billion p.a.). Patients fitted with cochlear implants suffer from similar limitations, and as the population ages more people are affected. It is clear that audio recognition and enhancement methods are required to stop us drowning in audio-data, for processing in hearing devices, and tosupport new technological innovations. Current approaches to these problems use a combination of audio signal processing (which places the audio data into a convenient format and reduces the data-rate) and machine learning (which removes noise, separates sources, or classifies the content). It is widely believed that these two fields must become increasingly integrated in the future. However, this union is currently a troubled one, suffering from four problems. Inefficiency: The methods are too inefficient when we have vast amounts of data (as is the case for audio-tracks on the web) or for real-time applications (such as is necessary in hearing aids)Impoverished models: The machine learning modules tend to be statistically limited.Unadapted: The signal processing modules are unadapted despite evidence from other fields, like computer vision, which suggests that automatic tuning leads to significant performance gains Distorted mixtures: The signal processing modules introduce non-linear distortions which are not captured by the machine learning modules.In this project we address these four limitations by introducing a new theoretical framework which unifies signal processing and machine learning. The key step is to view the signal processing module as solving an inference problem. Since the machine-learning modules are often framed in this way, the two modules can be integrated into a single coherent approach allowing technologies from the two fields to be completely integrated. In the project we will then use the new approach to develop efficient, rich, adaptive, and distortion free approaches to audio denoising, source separation and recognition. We will evaluate the the noise reduction and source separations algorithms on the hearing impaired, and the audio recognition algorithms on audio-sound track data.We believe this new framework will form a foundation of the emerging field of machine hearing. In the future, machine hearing will be deployed in a vast range of applications from music processing tasks to augmented reality systems (in conjunction with technologies from computer vision). We believe that this project will kick start this proliferation.

现代技术正在导致大量的音频数据，例如，每分钟都会将超过 72 小时的非结构化和未标记的音轨上传到互联网站点，因此迫切需要自动系统来识别音频内容，以便可以对这些音轨进行识别。此外，越来越多的录音是在包含多个声源和噪音的充满挑战的环境中通过手持设备进行的，因此需要自动系统来进行记录。清理音频内容并将音源与混合物分离 与此相关的是，听力障碍人士的设备目前在噪音方面表现不佳。事实上，这是英国 600 万人受益于助听器的主要原因。不要使用它们（每年价值 180 亿英镑的市场）。安装人工耳蜗的患者也面临着类似的限制，而且随着人口老龄化，越来越多的人受到影响，显然需要音频识别和增强方法来阻止我们淹没在音频中。 -数据，用于听力处理设备，并支持新技术创新，当前解决这些问题的方法结合使用音频信号处理（将音频数据转换为方便的格式并降低数据速率）和机器学习（消除噪声、分离源或人们普遍认为，这两个领域在未来必须变得越来越融合，但目前这一联盟存在着四个问题：当我们拥有大量数据时，这些方法效率太低。 （就像这样的情况网络上的音轨）或实时应用（例如助听器所必需的）贫困模型：机器学习模块往往在技术上受到限制。未适应：尽管有来自其他领域的证据，例如信号处理模块尚未适应计算机视觉，这表明自动调整会带来显着的性能提升。 混合失真：信号处理模块引入了机器学习模块无法捕获的非线性失真。在这个项目中，我们通过引入一个新的理论框架来解决这四个限制，统一信号关键步骤是将信号处理模块视为解决推理问题，因为机器学习模块通常以这种方式构建，因此可以将这两个模块集成到一个单一的连贯方法中，从而允许使用两个模块。在该项目中，我们将使用新方法开发高效、丰富、自适应且无失真的音频去噪、源分离和识别方法，我们将评估听力方面的降噪和源分离算法。受损，以及音频音轨上的音频识别算法我们相信，这个新框架将构成机器听觉新兴领域的基础。未来，机器听觉将被部署在从音乐处理任务到增强现实系统的广泛应用中（与计算机视觉技术相结合）。 ）我们相信这个项目将启动这种扩散。

项目成果

Infinite-Horizon Gaussian Processes

• 发表时间: 2018-11
• 作者: A. Solin;J. Hensman;Richard E. Turner

Sparse Gaussian Process Variational Autoencoders

稀疏高斯过程变分自动编码器

• DOI: 10.48550/arxiv.2010.10177
• 发表时间: 2020
• 作者: Ashman M

On Sparse Variational Methods and the Kullback-Leibler Divergence between Stochastic Processes

• DOI: 10.17863/cam.15597
• 发表时间: 2015-04
• 作者: A. G. Matthews;J. Hensman;Richard E. Turner;Zoubin Ghahramani

Deterministic Variational Inference for Robust Bayesian Neural Networks

• 发表时间: 2018-09
• 作者: Anqi Wu;Sebastian Nowozin;Edward Meeds;Richard E. Turner;José Miguel Hernández-Lobato;Alexander L. Gaunt

The Multivariate Generalised von Mises Distribution: Inference and Applications

• DOI: 10.1609/aaai.v31i1.10943
• 发表时间: 2016-02
• 期刊: ArXiv
• 作者: Alexandre K. W. Navarro;J. Frellsen;Richard E. Turner