BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning for Sounds - Akisato Kimura
DTSTART:20180111T133000Z
DTEND:20180111T150000Z
UID:TALK94231@talks.cam.ac.uk
CONTACT:Alessandro Davide Ialongo
DESCRIPTION:*Abstract*\n\nSince the great success in the ImageNet competit
 ion in 2012\, images have been the most popular applications of deep neura
 l networks. However\, deep learning for speech signal processing has alrea
 dy been developed since around 2009\, and several consumer products relate
 d to speech/music recognition and synthesis build on deep learning. In thi
 s reading group\, we review recent advances in deep learning for sounds ve
 ry briefly\, and introduce several papers related to sound representation 
 learning and synthesis with the help of pre-trained deep neural networks f
 or images.\n\n*Recommended Reading*\n\n* Owens\, Isola\, McDermott\, Torra
 lba\, Adelson\, Freeman\,\n "Visually indicated sounds\,"\n Proc. CVPR2016
 .\n https://arxiv.org/abs/1512.08512\n* Ayter\, Vondrick\, Torralba\,\n "S
 ee\, hear and read: Deep aligned representations\,"\n arXiv pre-print.\n h
 ttps://arxiv.org/abs/1706.00932\n* Ayter\, Vondrick\, Torralba\,\n "SoundN
 et: Learning sound representations from unlabeled video\,”\n Proc. NIPS2
 017.\n https://arxiv.org/abs/1610.09001
LOCATION:Engineering Department\, CBL Seminar Room 4-38
END:VEVENT
END:VCALENDAR