{"id":692004,"date":"2020-08-11T11:00:23","date_gmt":"2020-08-11T18:00:23","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=692004"},"modified":"2020-10-23T10:41:56","modified_gmt":"2020-10-23T17:41:56","slug":"forest-sound-scene-simulation-and-bird-localization-with-distributed-microphone-arrays","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/forest-sound-scene-simulation-and-bird-localization-with-distributed-microphone-arrays\/","title":{"rendered":"Forest Sound Scene Simulation and Bird Localization with Distributed Microphone Arrays"},"content":{"rendered":"<p>Audio-based wildlife monitoring is an important method for studying animal habitations and for the conservation of animal species and ecosystems. In this work, we have developed a highly efficient and scalable forest acoustics simulation algorithm, a dataset of bird audio clips and background noise clips extracted from two publicly available field recording databases, and a synthetic forest wildlife sound scene generator for distributed microphone array recording setups. We used the synthetic forest sound scenes to study the robustness of commonly used sound source localization algorithms in a wildlife monitoring setup in various reverberation, noise, and measurement error conditions. In our simulated bird localization experiments, we observed that the microphone spacing, signal-to-noise ratio, and the choice of the spectral weighting function in the localization algorithm have significant impact on localization accuracy, while the effect of synchronization error and microphone position misalignment was modest. We also observed that problem-specific spectral weighting in the localization algorithm and noise suppression pre-processing significantly improve the localization accuracy. These results are expected to help design practical wildlife monitoring systems and suggest promising directions for further improvements.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Audio-based wildlife monitoring is an important method for studying animal habitations and for the conservation of animal species and ecosystems. In this work, we have developed a highly efficient and scalable forest acoustics simulation algorithm, a dataset of bird audio clips and background noise clips extracted from two publicly available field recording databases, and a [&hellip;]<\/p>\n","protected":false},"featured_media":700717,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13561,243062,198583],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-692004","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-audio-acoustics","msr-research-area-ecology-environment","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/xEcZxtwDYzs","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/692004"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/692004\/revisions"}],"predecessor-version":[{"id":692010,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/692004\/revisions\/692010"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/700717"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=692004"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=692004"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=692004"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=692004"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=692004"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=692004"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}