《The challenge of realistic music generation: modelling raw audio at scale》论文阅读笔记
The challenge of realistic music generation: modelling raw audio at scale
作者:Deep mind三位大神
出处:NIPS 2018
- Abstract
首先提出了基于表达方式的音乐生成(high-level representations such as scoresor MIDI)有一些自己的问题,经过高度抽象后,音乐中的一些细节特征损失掉了,从而导致perception of musicality and realism 的损失。本文的音乐数据生成在raw audio domain中进行。autoregressive models(自回归模型)在处理波形speech数据中表现不俗,但在处理音乐时,we find them biased towards capturing local signal structure at the expense of modelling long-range correlations,于是本文提出autoregressive discrete autoencoders (ADAs) 帮助AR model capture long-range correlations in waveforms。
- Introduction
强调了music在不同的timescale上展现的structure特性,并且列出了midi等表示形式的限制,主要还是在丢失音乐性相关细节和乐器相关细节上。
1.1 raw audio signal
吹了一波wave signal的好处,优势,和上面提到的midi做比较,并指出在wave形式下建模更具挑战性和难度。
1.2 相关生成模型
相比于表示型数据,audio waveforms生成模型的研究历史并不长,原因是:This was long thought to be infeasible due to the scale of the problem, as audio signals are often sampled at rates of 16 kHz or higher(不太明白为什么,应该是采样成本较高). 近期的AR模型采用step步进的方式来进行生成,如Wavenet,VRNN,WaveRNN,SampleRNN,解决了采样成本的问题,这里也提到了用GAN来生成波形文件。
贡献:1.提出文献关注点较少的raw audio domain的生成模型,可以作为benchmark测试ability of a model to capture long-range structure in data
2. We investigate the capabilities of autoregressive models for this task, and demonstrate a computationally efficient method to enlarge their receptive fields using autoregressive discrete autoencoders (ADAs)
3. introduce the argmax autoencoder (AMAE) as an alternative to vector quantisation variational autoencoders (VQ-VAE)
- Scaling up autoregressive models for music
要为long-range structure建模,需要enlarge the receptive fields,wavenet,sampleRNN都提出自己的方式来扩大接受野,但内存限制很容易触及天花板
(未完待续)
重要参考文献:
Arecurrent latent variable model for sequential data
Experiments in musical intelligence
Synthesizing audio with generative adversarial networks
Samplernn: An unconditional end-to-end neural audio generation model
《The challenge of realistic music generation: modelling raw audio at scale》论文阅读笔记的更多相关文章
- 《MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment》论文阅读笔记
出处:2018 AAAI SourceCode:https://github.com/salu133445/musegan abstract: (写得不错 值得借鉴)重点阐述了生成音乐和生成图片,视频 ...
- (转)Introductory guide to Generative Adversarial Networks (GANs) and their promise!
Introductory guide to Generative Adversarial Networks (GANs) and their promise! Introduction Neural ...
- 生成对抗网络(Generative Adversarial Networks,GAN)初探
1. 从纳什均衡(Nash equilibrium)说起 我们先来看看纳什均衡的经济学定义: 所谓纳什均衡,指的是参与人的这样一种策略组合,在该策略组合上,任何参与人单独改变策略都不会得到好处.换句话 ...
- 生成对抗网络(Generative Adversarial Networks, GAN)
生成对抗网络(Generative Adversarial Networks, GAN)是一种深度学习模型,是近年来复杂分布上无监督学习最具前景的学习方法之一. GAN 主要包括了两个部分,即 ...
- StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks 论文笔记
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks 本文将利 ...
- 论文笔记之:Semi-Supervised Learning with Generative Adversarial Networks
Semi-Supervised Learning with Generative Adversarial Networks 引言:本文将产生式对抗网络(GAN)拓展到半监督学习,通过强制判别器来输出类 ...
- 《Self-Attention Generative Adversarial Networks》里的注意力计算
前天看了 criss-cross 里的注意力模型 仔细理解了 在: https://www.cnblogs.com/yjphhw/p/10750797.html 今天又看了一个注意力模型 < ...
- Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection
Perceptual Generative Adversarial Networks for Small Object Detection 2017-07-11 19:47:46 CVPR 20 ...
- SalGAN: Visual saliency prediction with generative adversarial networks
SalGAN: Visual saliency prediction with generative adversarial networks 2017-03-17 摘要:本文引入了对抗网络的对抗训练 ...
- Generative Adversarial Networks,gan论文的畅想
前天看完Generative Adversarial Networks的论文,不知道有什么用处,总想着机器生成的数据会有机器的局限性,所以百度看了一些别人 的看法和观点,可能我是机器学习小白吧,看完之 ...
随机推荐
- Html5学习笔记1 元素 标签 属性
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...
- flex操作XML,强力总结帖
初始化XML对象 XML对象可以代表一个XML元素.属性.注释.处理指令或文本元素.在ActionScript 3.0中我们可以直接将XML数据赋值给变量: var myXML:XML = &l ...
- Visual Studio 12无法调试Silverligh应用程序的问题
环境: Win7 Ultimate X64 Visual Studio 12 (以下简称 VS12) Internet Explorer 9(以下简称 IE9) Silverlight5_x64 ad ...
- cocos2d-x项目101次相遇:在HelloWorld上--建立新场景
cocos2d-x 101次相遇 / 文件夹 1 安装和环境搭建 -xcode 2 Scenes , Director, Layers, Sprites 3 建立图片菜单 4 在 ...
- Toad 使用中遇到的问题
1:智能提示: 视图-->toad选项-->Editor-->Code Assist-->Toad Insight---->sort pick list alphabet ...
- ARM Holdings
http://en.wikipedia.org/wiki/Advanced_RISC_Machines ARM Holdings (Redirected from Advanced RISC Mac ...
- OpenCV for Python 学习笔记 一
本人的学习笔记主要记录的是学习opencv-python-tutorials这本书中的笔记 今天晚上简单学习OpenCV for Python如何绘图,主要用了这几个函数(这几个函数可在:http:/ ...
- Canvas学习笔记——动画中的三角学
示例1,跟随鼠标的键头: 需要掌握一个重要的公式,这个方法返回从 x 轴到点 (x,y) 之间的角度 Math.atan2(dy,dx); 关键代码: function Arrow() { thi ...
- maven的坑: Exception in thread "pool-1-thread-1" java.lang.NoClassDefFoundError: org/eclipse/aether/spi/connector/Transfer$State
搭建ReboletricSample的环境: 搭建完成,执行的时候报错: Exception in thread "main" java.lang.NoClassDefFoundE ...
- 多媒体开发之---h.264 SPS PPS解析源代码,C实现一以及nal分析器
http://blog.csdn.net/mantis_1984/article/details/9465909 http://blog.csdn.net/arau_sh/article/detail ...