{"id":"https://openalex.org/W4392904037","doi":"https://doi.org/10.1109/icassp48485.2024.10445807","title":"Exploring Meta Information for Audio-Based Zero-Shot Bird Classification","display_name":"Exploring Meta Information for Audio-Based Zero-Shot Bird Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904037","doi":"https://doi.org/10.1109/icassp48485.2024.10445807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023952045","display_name":"Alexander Gebhard","orcid":"https://orcid.org/0000-0003-4169-5403"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"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":true,"raw_author_name":"Alexander Gebhard","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"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"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092897653","display_name":"Teresa Bez","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Teresa Bez","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034102826","display_name":"Lukas Christ","orcid":"https://orcid.org/0000-0002-8631-0186"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Christ","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056141709","display_name":"Alexander Kathan","orcid":"https://orcid.org/0000-0002-4757-2220"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Kathan","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"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"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023952045"],"corresponding_institution_ids":["https://openalex.org/I179225836","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.6243,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81609195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1211","last_page":"1215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7639733552932739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6802670359611511},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6004301905632019},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.418948769569397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4145699143409729},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3944772481918335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3466285467147827},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33989590406417847},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.33533385396003723},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27154096961021423},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19134536385536194},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12721166014671326}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7639733552932739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802670359611511},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6004301905632019},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.418948769569397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4145699143409729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3944772481918335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3466285467147827},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33989590406417847},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.33533385396003723},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27154096961021423},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19134536385536194},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12721166014671326}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W2102765684","https://openalex.org/W2171061940","https://openalex.org/W2398118205","https://openalex.org/W2970641574","https://openalex.org/W3121931845","https://openalex.org/W3138521398","https://openalex.org/W3176445421","https://openalex.org/W3196974791","https://openalex.org/W4212774754","https://openalex.org/W4213419599","https://openalex.org/W4226051760","https://openalex.org/W4284898017","https://openalex.org/W4289958244","https://openalex.org/W4312636570","https://openalex.org/W4372260106","https://openalex.org/W4372266552","https://openalex.org/W4372266808","https://openalex.org/W4386226099","https://openalex.org/W6678360021","https://openalex.org/W6678470764","https://openalex.org/W6755207826","https://openalex.org/W6784802156","https://openalex.org/W6791353385","https://openalex.org/W6802032897"],"related_works":["https://openalex.org/W4360764600","https://openalex.org/W1975359510","https://openalex.org/W4312624015","https://openalex.org/W1496727373","https://openalex.org/W2020952589","https://openalex.org/W1833351015","https://openalex.org/W1580526244","https://openalex.org/W1564601668","https://openalex.org/W2365659558","https://openalex.org/W4252085734"],"abstract_inverted_index":{"Advances":[0],"in":[1],"passive":[2],"acoustic":[3],"monitoring":[4],"and":[5,29,56,76,91,116,138],"machine":[6],"learning":[7,120],"have":[8],"led":[9],"to":[10,51,94,124,155],"the":[11,52,95,98,110,126,136],"procurement":[12],"of":[13,54,64,97,146],"vast":[14],"datasets":[15],"for":[16,27],"computational":[17],"bioacoustic":[18],"research.":[19],"Nevertheless,":[20],"data":[21],"scarcity":[22],"is":[23],"still":[24],"an":[25,46],"issue":[26],"rare":[28],"underrepresented":[30],"species.":[31],"This":[32],"study":[33,49],"investigates":[34],"how":[35],"meta-information":[36],"can":[37],"improve":[38],"zero-shot":[39,119],"audio":[40,82,86],"classification,":[41],"utilising":[42],"bird":[43,67,77],"species":[44],"as":[45,113],"example":[47],"case":[48],"due":[50],"availability":[53],"rich":[55],"diverse":[57],"meta-data.":[58],"We":[59],"investigate":[60],"three":[61],"different":[62,150],"sources":[63],"metadata:":[65],"textual":[66],"sound":[68],"descriptions":[69],"encoded":[70],"via":[71],"(S)Bert,":[72],"functional":[73],"traits":[74],"(Avonet),":[75],"life-history":[78],"(BLH)":[79],"characteristics.":[80],"As":[81],"features,":[83],"we":[84,108],"extract":[85],"spectrogram":[87],"transformer":[88],"(AST)":[89],"embeddings":[90],"project":[92],"them":[93],"dimension":[96],"auxiliary":[99],"information":[100],"by":[101,134],"adopting":[102],"a":[103,117,142],"single":[104],"linear":[105],"layer.":[106],"Then,":[107],"employ":[109],"dot":[111],"product":[112],"compatibility":[114],"function":[115],"standard":[118],"ranking":[121],"hinge":[122],"loss":[123],"determine":[125],"correct":[127],"class.":[128],"The":[129],"best":[130],"results":[131],"are":[132],"achieved":[133],"concatenating":[135],"Avonet":[137],"BLH":[139],"features":[140],"attaining":[141],"mean":[143],"unweighted":[144],"F1-score":[145],".233":[147],"over":[148],"five":[149],"test":[151],"sets":[152],"with":[153],"8":[154],"10":[156],"classes.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}