{"id":"https://openalex.org/W2799799485","doi":"https://doi.org/10.1109/icassp.2018.8462156","title":"Automatic Bird Vocalization Identification Based on Fusion of Spectral Pattern and Texture Features","display_name":"Automatic Bird Vocalization Identification Based on Fusion of Spectral Pattern and Texture Features","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2799799485","doi":"https://doi.org/10.1109/icassp.2018.8462156","mag":"2799799485"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5076638108","display_name":"Sai-hua Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sai-hua Zhang","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358624","display_name":"Zhao Zhao","orcid":"https://orcid.org/0000-0001-7901-500X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhao","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743347","display_name":"Zhiyong Xu","orcid":"https://orcid.org/0000-0002-5722-8271"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-yong Xu","raw_affiliation_strings":["School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Optical Engineering, Nanjing University Sci. & Technol., China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083223656","display_name":"Kristen Bellisario","orcid":"https://orcid.org/0000-0002-9810-3504"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Bellisario","raw_affiliation_strings":["Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029912679","display_name":"Bryan C. Pijanowski","orcid":"https://orcid.org/0000-0002-7089-1959"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan C. Pijanowski","raw_affiliation_strings":["Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076638108"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":3.4787,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.92550505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9998000264167786,"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":0.9998000264167786,"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/T10659","display_name":"Marine animal studies overview","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"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":0.9803000092506409,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.785010814666748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7645321488380432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6914311647415161},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6594606041908264},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5781118869781494},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.524830162525177},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4982490539550781},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49528804421424866},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.4750792384147644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4723566472530365},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4667288064956665},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4471660554409027},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4439787268638611},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4400624632835388},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4331432282924652},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4245809018611908},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1685955822467804}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.785010814666748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7645321488380432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914311647415161},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6594606041908264},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5781118869781494},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.524830162525177},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4982490539550781},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49528804421424866},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.4750792384147644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4723566472530365},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4667288064956665},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4471660554409027},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4439787268638611},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4400624632835388},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4331432282924652},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4245809018611908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1685955822467804},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320327240","display_name":"Liga Portuguesa Contra o Cancro","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W349459512","https://openalex.org/W1500895378","https://openalex.org/W1527909365","https://openalex.org/W1607979445","https://openalex.org/W1808644423","https://openalex.org/W2039261343","https://openalex.org/W2048542643","https://openalex.org/W2048747935","https://openalex.org/W2050844722","https://openalex.org/W2073546306","https://openalex.org/W2088328344","https://openalex.org/W2111751070","https://openalex.org/W2115891142","https://openalex.org/W2117200996","https://openalex.org/W2117863804","https://openalex.org/W2121452312","https://openalex.org/W2150521923","https://openalex.org/W2172000360","https://openalex.org/W2208475249","https://openalex.org/W2271175897","https://openalex.org/W2289954099","https://openalex.org/W2344121590","https://openalex.org/W2579586206","https://openalex.org/W2607308654","https://openalex.org/W4297989434","https://openalex.org/W6631844364","https://openalex.org/W6636492697","https://openalex.org/W6639731134","https://openalex.org/W6662573422","https://openalex.org/W6663172427","https://openalex.org/W6682282127"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2970653563","https://openalex.org/W3093766508","https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W2075383893","https://openalex.org/W3044690502"],"abstract_inverted_index":{"Automatic":[0],"bird":[1,102,106],"species":[2,119],"identification":[3],"from":[4],"audio":[5,94],"field":[6,98],"recordings":[7,99],"is":[8],"studied":[9],"in":[10,74],"this":[11],"paper.":[12],"We":[13],"first":[14],"used":[15,92],"a":[16,46,78],"Gaussian":[17],"mixture":[18],"model":[19],"(GMM)":[20],"based":[21],"energy":[22],"detector":[23],"to":[24,53,115],"select":[25,54],"representative":[26],"acoustic":[27,107],"events.":[28],"Two":[29],"different":[30],"feature":[31,48,81],"sets":[32],"consisting":[33],"of":[34,69,77,97,100,130],"spectral":[35,79],"pattern":[36,80],"and":[37,109],"texture":[38,84],"features":[39],"were":[40],"extracted":[41],"for":[42,141],"each":[43],"event.":[44],"Then,":[45],"ReliefF-based":[47],"selection":[49],"algorithm":[50],"was":[51,59],"employed":[52],"distinguishing":[55],"features.":[56],"Finally,":[57],"classification":[58,125],"performed":[60],"using":[61],"support":[62],"vector":[63],"machine":[64],"(SVM).":[65],"The":[66],"main":[67],"focus":[68],"the":[70,75,131,136],"proposed":[71,137],"method":[72,138],"lies":[73],"fusion":[76],"with":[82,128],"several":[83],"descriptors,":[85],"which":[86,134],"extends":[87],"our":[88],"previous":[89],"work.":[90],"Experiments":[91],"an":[93],"dataset":[95],"comprised":[96],"11":[101],"species,":[103],"containing":[104],"2762":[105],"events":[108,113],"339":[110],"detected":[111],"\u201cunknown\u201d":[112],"(corresponding":[114],"noise":[116],"or":[117],"unknown":[118],"vocalizations).":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"superior":[124],"performance":[126],"compared":[127],"that":[129],"state-of-the-art":[132],"method,":[133],"renders":[135],"more":[139],"suitable":[140],"real-field":[142],"recording":[143],"analysis.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}