[B06] Learning soft-attention models for tempo-invariant audio-sheet music retrieval
"The amount of temporal context given to a CNN is adapted by an additional soft-attention network, enabling the network to react to local and global tempo deviations in the input audio spectrogram."
presenter ISMIR2019
11/5/2019 1:20:00 PM

Mediasite Showcase
Mediasite's the trusted cornerstone of any campus or enterprise video strategy. Our unyielding commitment to all things video helps you transform education, training, communications and online events.
Webcasting Video Content Management Video Delivery Integration Services Mediasite Community
Powered By Mediasite - Enterprise Video Platform
Sonic Foundry