Machine Learning for Sounds
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Alessandro Davide Ialongo.
Abstract
Since the great success in the ImageNet competition in 2012, images have been the most popular applications of deep neural networks. However, deep learning for speech signal processing has already been developed since around 2009, and several consumer products related to speech/music recognition and synthesis build on deep learning. In this reading group, we review recent advances in deep learning for sounds very briefly, and introduce several papers related to sound representation learning and synthesis with the help of pre-trained deep neural networks for images.
Recommended Reading
- Owens, Isola, McDermott, Torralba, Adelson, Freeman,
“Visually indicated sounds,”
Proc. CVPR2016 .
https://arxiv.org/abs/1512.08512
- Ayter, Vondrick, Torralba,
“See, hear and read: Deep aligned representations,”
arXiv pre-print.
https://arxiv.org/abs/1706.00932
- Ayter, Vondrick, Torralba,
“SoundNet: Learning sound representations from unlabeled video,”
Proc. NIPS2017 .
https://arxiv.org/abs/1610.09001
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|