| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 16 Nov 2018 11:40:01 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"5beeac91-933"
expires: Mon, 29 Dec 2025 06:45:05 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 6422:1F53DD:86463E:96E875:69522118
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 06:35:05 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210031-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766990105.372558,VS0,VE233
vary: Accept-Encoding
x-fastly-request-id: 5c8f4b938ef441c61850e5bcec0717d9a700294c
content-length: 1011
Audio samples from "Autoencoder-based Music Translation"
Abstract
We present a method for translating music across musical instruments and styles. This method is based on unsupervised training of 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 also from musical domains that were not seen during training. We evaluate our method on a dataset collected from professional musicians, and achieve convincing translations. We also study the properties of the obtained translation and demonstrate translating even from a whistle, potentially enabling the creation of instrumental music by untrained humans.