In this study, we evaluated deep convolutional neural networks for classifying the calls of 24 birds and amphibian species detected in ambient field recordings from the tropical mountains of Puerto Rico. Training data were collected using a template-based detection algorithm followed by a manual validation process. As preparing sufficient training data is a major challenge for many deep learning applications, we propose a novel approach that combines transfer learning of a pre-trained deep convolutional neural network (CNN) model and a semi-supervised pseudo-labeling method with a custom loss function to meet this challenge. Our proposed methodology enables the network to be trained in a supervised fashion with labeled and unlabeled data simultaneously, which effectively increases the size of training set and thus boosts the model performance. In classifying a test set of manually validated positive and negative template-based detections, our proposed model achieves 97.7% sensitivity (true positive rate), 96.4% specificity (true negative rate) and 99.5% Area Under a Curve (AUC). This multi-label multi-species classification methodology and its framework can be easily adopted by other acoustic classification problems.<\/p>\n","protected":false},"excerpt":{"rendered":"
In this study, we evaluated deep convolutional neural networks for classifying the calls of 24 birds and amphibian species detected in ambient field recordings from the tropical mountains of Puerto Rico. Training data were collected using a template-based detection algorithm followed by a manual validation process. As preparing sufficient training data is a major challenge […]<\/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":[13556,243062,198583],"msr-publication-type":[193715],"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-696769","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-audio-acoustics","msr-research-area-ecology-environment","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-9-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"Applied Acoustics","msr_volume":"166","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":"doi","viewUrl":"false","id":"false","title":"https:\/\/doi.org\/10.1016\/j.apacoust.2020.107375","label_id":"243109","label":0}],"msr_related_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/github.com\/microsoft\/Multi_Species_Bioacoustic_Classification","label_id":"264520","label":0}],"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Ming Zhong","user_id":39721,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ming Zhong"},{"type":"text","value":"Jack LeBien","user_id":0,"rest_url":false},{"type":"text","value":"Marconi Campos-Cerqueira","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Rahul Dodhia","user_id":41401,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Rahul Dodhia"},{"type":"user_nicename","value":"Juan M. Lavista Ferres","user_id":39552,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Juan M. Lavista Ferres"},{"type":"text","value":"Julian P.Velev","user_id":0,"rest_url":false},{"type":"text","value":"T. Mitchell Aide","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[696544],"msr_project":[1016418,784627,597754],"publication":[],"video":[],"download":[],"msr_publication_type":"article","related_content":{"projects":[{"ID":1016418,"post_title":"Advance Sustainability - AI for Good","post_name":"advance-sustainability-ai-for-good","post_type":"msr-project","post_date":"2024-04-02 08:57:43","post_modified":"2024-11-27 10:34:16","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/advance-sustainability-ai-for-good\/","post_excerpt":"Climate change requires swift, collective action and technological innovation. We are committed to meeting our own goals while enabling others to do the same.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1016418"}]}},{"ID":784627,"post_title":"Bioacoustics","post_name":"bioacoustics","post_type":"msr-project","post_date":"2021-12-17 10:04:48","post_modified":"2024-06-06 18:56:29","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/bioacoustics\/","post_excerpt":"Bioacoustics is a cross-disciplinary science that combines biology and acoustics. Usually, it refers to the investigation of sound production, dispersion and reception in animals (including humans). In our research lab, we collaborate with conservation organizations and research labs to leverage machine learning and deep learning models to automatically process and analyze large volumes of audio recordings.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/784627"}]}},{"ID":597754,"post_title":"Accelerating Biodiversity Surveys with AI","post_name":"accelerating-biodiversity-surveys","post_type":"msr-project","post_date":"2020-02-19 09:03:12","post_modified":"2022-03-21 15:32:01","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/accelerating-biodiversity-surveys\/","post_excerpt":"Biodiversity is declining across the globe at a catastrophic rate, as threats from human settlement expansion, illegal wildlife killing, and climate change place enormous pressure on wildlife populations. Conservation biologists are faced with the daunting \u2013 but urgent \u2013 task of surveying wildlife populations and making policy recommendations to governments and industry. What species need legal protection from hunting? A road needs to connect two cities; which route will have the least detrimental impact on…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/597754"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/696769","targetHints":{"allow":["GET"]}}],"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":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/696769\/revisions"}],"predecessor-version":[{"id":903588,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/696769\/revisions\/903588"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=696769"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=696769"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=696769"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=696769"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=696769"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=696769"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=696769"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=696769"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=696769"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=696769"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=696769"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=696769"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=696769"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=696769"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=696769"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=696769"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}