{"id":"https://openalex.org/W2114806403","doi":"https://doi.org/10.1109/icassp.2011.5946409","title":"Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations","display_name":"Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2114806403","doi":"https://doi.org/10.1109/icassp.2011.5946409","mag":"2114806403"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1107326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, 80290, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, 80290, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, 80290, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, 80290, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10838","display_name":"Animal Behavior and Welfare Studies","score":0.9350000023841858,"subfield":{"id":"https://openalex.org/subfields/3404","display_name":"Small Animals"},"field":{"id":"https://openalex.org/fields/34","display_name":"Veterinary"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733524441719055},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7026432156562805},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.696670413017273},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6304667592048645},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5726058483123779},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5710409283638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5257590413093567},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5177918672561646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4936893880367279},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4600730836391449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3537580370903015},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3489850163459778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733524441719055},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7026432156562805},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.696670413017273},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6304667592048645},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5726058483123779},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5710409283638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5257590413093567},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5177918672561646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936893880367279},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4600730836391449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537580370903015},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3489850163459778},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5946409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.5330","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.5330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/11/11wen2.pdf","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1107326","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1107326","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72683","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72683","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1107326","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1107326","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1594892530","https://openalex.org/W1602510806","https://openalex.org/W1987048275","https://openalex.org/W2064555134","https://openalex.org/W2066629230","https://openalex.org/W2085662862","https://openalex.org/W2122979854","https://openalex.org/W2133990480","https://openalex.org/W2162499636","https://openalex.org/W2162753443","https://openalex.org/W2168441989","https://openalex.org/W2293202270","https://openalex.org/W2917915438","https://openalex.org/W6635397529","https://openalex.org/W6697171384","https://openalex.org/W6759808675"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"We":[0,51],"present":[1],"a":[2,14,27,117,123],"study":[3],"on":[4,13,116,122],"purely":[5],"data-based":[6],"recognition":[7],"of":[8,29,43,48,66],"animal":[9],"sounds,":[10],"performing":[11],"evaluation":[12],"real-world":[15],"database":[16],"obtained":[17],"from":[18],"the":[19,32,35,44,49],"Humboldt-University":[20],"Animal":[21],"Sound":[22],"Archive.":[23],"As":[24],"we":[25,73],"avoid":[26],"preselection":[28],"friendly":[30],"cases,":[31],"challenge":[33],"for":[34,59],"classifiers":[36],"is":[37],"to":[38,112],"discriminate":[39],"between":[40],"species":[41],"regardless":[42],"age":[45],"or":[46],"stance":[47],"animal.":[50],"define":[52],"classification":[53,78,106],"tasks":[54],"that":[55],"can":[56],"be":[57],"useful":[58],"information":[60],"retrieval":[61],"and":[62,76,81,93,107,119],"indexing,":[63],"facilitating":[64],"categorization":[65],"large":[67],"sound":[68,105],"archives.":[69],"On":[70],"these":[71],"tasks,":[72],"compare":[74],"dynamic":[75],"static":[77],"by":[79],"left-right":[80],"cyclic":[82],"Hidden":[83],"Markov":[84],"Models,":[85],"recurrent":[86],"neural":[87],"networks":[88],"with":[89],"Long":[90],"Short-Term":[91],"Memory,":[92],"Support":[94],"Vector":[95],"Machines,":[96],"as":[97,99],"well":[98],"different":[100],"features":[101],"commonly":[102],"found":[103],"in":[104],"speech":[108],"recognition,":[109],"achieving":[110],"up":[111],"81.3":[113],"%":[114,121],"accuracy":[115],"2-class,":[118],"64.0":[120],"5-class":[124],"task.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
