{"id":651183,"date":"2020-04-19T14:51:28","date_gmt":"2020-04-19T21:51:28","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=651183"},"modified":"2021-09-27T10:38:43","modified_gmt":"2021-09-27T17:38:43","slug":"fast-acoustic-scattering-using-convolutional-neural-networks","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/fast-acoustic-scattering-using-convolutional-neural-networks\/","title":{"rendered":"Fast acoustic scattering using convolutional neural networks"},"content":{"rendered":"<p>Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation. We propose training a convolutional neural network to map from a convex scatterer&#8217;s cross-section to a 2D slice of the resulting spatial loudness distribution. We show that employing a full-resolution residual network for the resulting image-to-image regression problem yields spatially detailed loudness fields with a root-mean-squared error of less than 1 dB, at over 100x speedup compared to full wave simulation.<\/p>\n<div id=\"attachment_651189\" style=\"width: 783px\" class=\"wp-caption alignnone\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-651189\" class=\" wp-image-651189\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/ScatteringCNN-300x116.png\" alt=\"\" width=\"773\" height=\"299\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/ScatteringCNN-300x116.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/ScatteringCNN-1024x396.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/ScatteringCNN-768x297.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/ScatteringCNN.png 1470w\" sizes=\"(max-width: 773px) 100vw, 773px\" \/><p id=\"caption-attachment-651189\" class=\"wp-caption-text\">Given input binary image (left) representing object cross section, our CNN produces output acoustic fields for octave frequency bands (right, bottom row) that match closely with reference wave simulation (right, top row)<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation. We propose training a convolutional neural network to map from a convex scatterer&#8217;s cross-section to a 2D slice of the resulting spatial loudness distribution. We show that employing a full-resolution residual network for the resulting [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[243062],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-651183","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-audio-acoustics","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-5-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/Acoustic-Scattering-CNN.pdf","id":"651186","title":"acoustic-scattering-cnn","label_id":"243132","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":651186,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/04\/Acoustic-Scattering-CNN.pdf"}],"msr-author-ordering":[{"type":"text","value":"Ziqi Fan","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Vibhav Vineet","user_id":37751,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Vibhav Vineet"},{"type":"user_nicename","value":"Hannes Gamper","user_id":31943,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hannes Gamper"},{"type":"user_nicename","value":"Nikunj Raghuvanshi","user_id":33106,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nikunj Raghuvanshi"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[694407,714067],"msr_project":[546345],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":546345,"post_title":"Project Triton","post_name":"project-triton","post_type":"msr-project","post_date":"2018-12-03 12:03:07","post_modified":"2024-04-03 12:34:47","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/project-triton\/","post_excerpt":"Project Triton performs physical simulation to provide sound propagation for games and mixed reality. It creates an accurate acoustic rendering at practical CPU cost and provides designer control.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/546345"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/651183"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/651183\/revisions"}],"predecessor-version":[{"id":651192,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/651183\/revisions\/651192"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=651183"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=651183"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=651183"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=651183"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=651183"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=651183"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=651183"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=651183"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=651183"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=651183"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=651183"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=651183"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=651183"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=651183"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=651183"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=651183"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}