Archives/papers-we-love_papers-we-love
1
0
Fork 0
mirror of https://github.com/papers-we-love/papers-we-love.git synced 2024-10-27 20:34:20 +00:00
Code Issues Projects Releases Wiki Activity

Update README.md (#790)

Browse Source 
Add Attention is all You need Paper. 


Co-authored-by: Zeeshan Lakhani <zeeshan.lakhani@gmail.com>
Co-authored-by: Eric Leung <2754821+erictleung@users.noreply.github.com>
This commit is contained in:
Ravi Singh 2024-09-12 00:42:57 +05:30 committed by GitHub
parent 74ecbc8585
commit c3f44ae579
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
artificial_intelligence/README.md
View File

@ -13,3 +13,5 @@
* [A Universal Music Translation Network (2018)](https://arxiv.org/pdf/1805.07848.pdf) by Noam Mor, Lior Wolf, Adam Polyak & Yaniv Taigman * [A Universal Music Translation Network (2018)](https://arxiv.org/pdf/1805.07848.pdf) by Noam Mor, Lior Wolf, Adam Polyak & Yaniv Taigman
> This paper proposes a method for translating music across musical instruments, genres, and styles. It 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 enables translation 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. This method is evaluated 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. > This paper proposes a method for translating music across musical instruments, genres, and styles. It 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 enables translation 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. This method is evaluated 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.
* [Attention is all you need](http://papers.neurips.cc/paper/7181-attention-is-all-you-need.pdf) by Ashish Vaswani et al.