A Universal Music Translation Network
A Universal Music Translation Network
复制标题
环球音乐翻译网络
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Yaniv Taigman
中科院分区：
文献类型：
--
作者：
Noam Mor;Lior Wolf;Adam Polyak;Yaniv Taigman
我们提出了一种跨乐器、流派和风格翻译音乐的方法。该方法基于多域波网自动编码器，具有共享编码器和在波形上进行端到端训练的解缠结潜在空间。采用多样化的训练数据集和大的净容量，领域无关的编码器甚至允许我们从训练期间未见过的音乐领域进行翻译。该方法是无监督的，并且不依赖于域或音乐转录之间匹配样本形式的监督。我们在 NSynth 以及从专业音乐家收集的数据集上评估我们的方法，并实现令人信服的翻译，即使是从口哨翻译时，也可能使未经训练的人能够创作器乐。
We present a method for translating music across musical instruments, genres, and styles. This method is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-independent encoder allows us to translate even from musical domains that were not seen during training. The method is unsupervised and does not rely on supervision in the form of matched samples between domains or musical transcriptions. We evaluate our method on NSynth, as well as on a dataset collected from professional musicians, and achieve convincing translations, even when translating from whistling, potentially enabling the creation of instrumental music by untrained humans.
深度（呃）学习。
DOI：
10.1523/jneurosci.0153-18.2018
发表时间：
2018
期刊：
The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子：
--
作者：
Srinivasan,Shyam;Greenspan,RalphJ;Stevens,CharlesF;Grover,Dhruv
通讯作者：
Grover,Dhruv