{"id":"https://openalex.org/W7116056927","doi":"https://doi.org/10.1016/j.ecoinf.2025.103554","title":"Human Auditory Representation Learning for cross-dialect bird species recognition","display_name":"Human Auditory Representation Learning for cross-dialect bird species recognition","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7116056927","doi":"https://doi.org/10.1016/j.ecoinf.2025.103554"},"language":"en","primary_location":{"id":"doi:10.1016/j.ecoinf.2025.103554","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ecoinf.2025.103554","pdf_url":null,"source":{"id":"https://openalex.org/S195809937","display_name":"Ecological Informatics","issn_l":"1574-9541","issn":["1574-9541","1878-0512"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ecological Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.ecoinf.2025.103554","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xingfeng Li","orcid":"https://orcid.org/0000-0002-8958-0341"},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Xingfeng Li","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China"],"raw_orcid":"https://orcid.org/0000-0002-8958-0341","affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ningfeng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Ningfeng Luo","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feifei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Feifei Yu","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data Science, City University of Macau, 999078, Macao Special Administrative Region of China","institution_ids":["https://openalex.org/I6469544"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131870","display_name":"Institute of Psychology, Chinese Academy of Sciences","ror":"https://ror.org/03j7v5j15","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210131870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Li","raw_affiliation_strings":["Institute of Psychology, Chinese Academy of Sciences, Beijing, 100101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Psychology, Chinese Academy of Sciences, Beijing, 100101, China","institution_ids":["https://openalex.org/I4210131870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhao","raw_affiliation_strings":["School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaohan Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaohan Shi","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, 464-8601, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I6469544"],"apc_list":{"value":2510,"currency":"USD","value_usd":2510},"apc_paid":{"value":2510,"currency":"USD","value_usd":2510},"fwci":1.4719,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87494515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"93","issue":null,"first_page":"103554","last_page":"103554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9955000281333923,"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":0.9955000281333923,"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/T10895","display_name":"Species Distribution and Climate Change","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6899999976158142},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6033999919891357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4684000015258789},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3921000063419342},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3856000006198883},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.3815999925136566},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959999799728394},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6899999976158142},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6033999919891357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C205312793","wikidata":"https://www.wikidata.org/wiki/Q16002801","display_name":"Ambient noise level","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.ecoinf.2025.103554","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ecoinf.2025.103554","pdf_url":null,"source":{"id":"https://openalex.org/S195809937","display_name":"Ecological Informatics","issn_l":"1574-9541","issn":["1574-9541","1878-0512"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ecological Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.ecoinf.2025.103554","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ecoinf.2025.103554","pdf_url":null,"source":{"id":"https://openalex.org/S195809937","display_name":"Ecological Informatics","issn_l":"1574-9541","issn":["1574-9541","1878-0512"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ecological Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1968707255","https://openalex.org/W1970053778","https://openalex.org/W1985984415","https://openalex.org/W2003837604","https://openalex.org/W2004930422","https://openalex.org/W2013797913","https://openalex.org/W2042211079","https://openalex.org/W2103782808","https://openalex.org/W2130113542","https://openalex.org/W2194775991","https://openalex.org/W2525234067","https://openalex.org/W2607308654","https://openalex.org/W2883595988","https://openalex.org/W2913560175","https://openalex.org/W2962754725","https://openalex.org/W2964051877","https://openalex.org/W2971461653","https://openalex.org/W2994125460","https://openalex.org/W3088886402","https://openalex.org/W3090048552","https://openalex.org/W3094550259","https://openalex.org/W3100801259","https://openalex.org/W3104219138","https://openalex.org/W3121931845","https://openalex.org/W3157429491","https://openalex.org/W3185673854","https://openalex.org/W3195409179","https://openalex.org/W3207704044","https://openalex.org/W4206462062","https://openalex.org/W4280651134","https://openalex.org/W4282978184","https://openalex.org/W4292411597","https://openalex.org/W4296106947","https://openalex.org/W4309293828","https://openalex.org/W4310075934","https://openalex.org/W4313061427","https://openalex.org/W4386226099","https://openalex.org/W4390858462","https://openalex.org/W4392028727","https://openalex.org/W4392123750","https://openalex.org/W4393187136","https://openalex.org/W4402666012","https://openalex.org/W4408222464","https://openalex.org/W4411957310","https://openalex.org/W4413209844"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"bird":[1,20,242,254,262,284],"species":[2,226,243,263],"recognition":[3,227],"(BSR)":[4],"is":[5,13,23],"crucial":[6],"for":[7,92,203,221,286],"biodiversity":[8,222],"monitoring,":[9,223],"but":[10],"its":[11],"accuracy":[12,259],"often":[14],"hampered":[15],"by":[16,57,82,136,175,272],"geographic":[17],"variation":[18],"in":[19,39,51,127,260,276],"vocalizations,":[21],"which":[22],"frequently":[24],"described":[25],"as":[26],"dialectal":[27],"at":[28],"the":[29,35,74,155,168],"population":[30],"level.":[31],"This":[32],"work":[33],"uses":[34],"term":[36],"dialect":[37,68],"region":[38],"an":[40],"operational":[41],"sense":[42],"to":[43,45,65,72,111,117,146,177,196,240,251],"refer":[44],"geographically":[46],"separated":[47],"recording":[48],"regions":[49,81],"defined":[50],"benchmark":[52,157],"corpora":[53],"that":[54,105,209],"are":[55,134],"dominated":[56],"different":[58],"vocal":[59,266],"variants":[60],"across":[61,78,190,228,264],"populations,":[62],"rather":[63],"than":[64],"fine-grained,":[66],"species-specific":[67],"types.":[69],"We":[70,96],"aim":[71],"address":[73],"challenge":[75],"of":[76],"generalizing":[77],"such":[79],"dialect-dominated":[80],"introducing":[83],"a":[84,103,137,142,216],"novel":[85],"approach":[86,169],"leveraging":[87],"well-established":[88],"auditory-inspired":[89,237],"features":[90,110,239],"known":[91],"their":[93,121],"computational":[94],"robustness.":[95],"propose":[97],"Human":[98],"Auditory":[99],"Representation":[100],"Learning":[101],"(HARL),":[102],"framework":[104],"integrates":[106],"Gammatone-":[107],"and":[108,115,124,158,166,181,185,218,231,282],"Mel-spectrogram":[109],"capture":[112,252],"frequency":[113],"selectivity":[114],"invariance":[116],"acoustic":[118,232],"variations":[119],"through":[120],"spectral":[122],"efficiency":[123],"empirical":[125],"success":[126],"audio":[128],"processing.":[129],"These":[130,206],"complementary":[131],"auditory":[132],"representations":[133],"processed":[135],"dual-stream":[138],"ResNet50":[139],"architecture,":[140],"with":[141,212,249],"multi-head":[143],"attention":[144,250],"mechanism":[145],"emphasize":[147],"discriminative":[148],"spectral\u2013temporal":[149],"patterns.":[150,256],"In":[151],"cross-dialect":[152,277],"evaluation":[153],"on":[154,161,179,183],"D3BV":[156,180],"cross-site":[159],"tests":[160],"two":[162],"field":[163],"datasets":[164],"(S1":[165],"S2),":[167],"outperformed":[170],"strong":[171],"baselines,":[172],"raising":[173],"F1-score":[174,275],"up":[176],"24.31%":[178],"28.23%":[182],"S1":[184],"S2.":[186],"Performance":[187],"remained":[188],"stable":[189],"noise":[191],"conditions":[192],"from":[193],"\u2212":[194],"10":[195],"+10":[197],"dB":[198],"signal-to-noise":[199],"ratio,":[200],"indicating":[201],"robustness":[202],"real-world":[204],"deployment.":[205],"findings":[207],"showed":[208],"bridging":[210],"HARL":[211],"deep":[213,247],"learning":[214,248],"delivered":[215],"scalable":[217,281],"accurate":[219],"solution":[220],"enabling":[224],"reliable":[225,283],"diverse":[229],"geographies":[230],"conditions.":[233],"\u2022":[234,245,257,268,279],"Combines":[235],"human":[236],"sound":[238,255],"enhance":[241],"recognition.":[244],"Uses":[246],"complex":[253],"Improves":[258],"recognizing":[261],"regional":[265],"dialects.":[267],"Outperforms":[269],"baseline":[270],"methods":[271],"over":[273],"20%":[274],"settings.":[278],"Enables":[280],"monitoring":[285],"ecological":[287],"conservation.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-02-03T00:53:05.648605","created_date":"2025-12-19T00:00:00"}