{"id":17298,"date":"2017-06-21T07:20:44","date_gmt":"2017-06-21T04:20:44","guid":{"rendered":"https:\/\/hgpu.org\/?p=17298"},"modified":"2017-06-21T07:20:44","modified_gmt":"2017-06-21T04:20:44","slug":"kapre-on-gpu-audio-preprocessing-layers-for-a-quick-implementation-of-deep-neural-network-models-with-keras","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=17298","title":{"rendered":"Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras"},"content":{"rendered":"<p>We introduce Kapre, Keras layers for audio and music signal preprocessing. Music research using deep neural networks requires a heavy and tedious preprocessing stage, for which audio processing parameters are often ignored in parameter optimisation. To solve this problem, Kapre implements time-frequency conversions, normalisation, and data augmentation as Keras layers. We report simple benchmark results, showing real-time on-GPU preprocessing adds a reasonable amount of computation.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We introduce Kapre, Keras layers for audio and music signal preprocessing. Music research using deep neural networks requires a heavy and tedious preprocessing stage, for which audio processing parameters are often ignored in parameter optimisation. To solve this problem, Kapre implements time-frequency conversions, normalisation, and data augmentation as Keras layers. We report simple benchmark results, [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,89,3,41],"tags":[1782,14,1673,1930,34,20,1898,1767,176,513,1789,1740,1928],"class_list":["post-17298","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","category-signal-processing","tag-computer-science","tag-cuda","tag-deep-learning","tag-keras","tag-neural-networks","tag-nvidia","tag-nvidia-geforce-gtx-1080","tag-nvidia-geforce-gtx-titan-x","tag-package","tag-python","tag-signal-processing","tag-tesla-k80","tag-tesla-m60"],"views":2450,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17298","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=17298"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17298\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17298"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17298"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17298"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}