{"id":"https://openalex.org/W2620221678","doi":"https://doi.org/10.1109/taslp.2017.2690562","title":"Spectrogram Enhancement Using Multiple Window Savitzky-Golay (MWSG) Filter for Robust Bird Sound Detection","display_name":"Spectrogram Enhancement Using Multiple Window Savitzky-Golay (MWSG) Filter for Robust Bird Sound Detection","publication_year":2017,"publication_date":"2017-05-23","ids":{"openalex":"https://openalex.org/W2620221678","doi":"https://doi.org/10.1109/taslp.2017.2690562","mag":"2620221678"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2690562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690562","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/73400/1/MPRA_paper_73400.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]},{"id":"https://openalex.org/I42014448","display_name":"Sardar Vallabhbhai National Institute of Technology Surat","ror":"https://ror.org/02y394t43","country_code":"IN","type":"education","lineage":["https://openalex.org/I42014448"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["Electronics and Communication Engineering, National Institute of Technology, Surathkal, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Communication Engineering, National Institute of Technology, Surathkal, Karnataka, India","institution_ids":["https://openalex.org/I11880225","https://openalex.org/I42014448"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113010885","display_name":"G. Meenakshi","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G. Nisha Meenakshi","raw_affiliation_strings":["Indian Institute of Science, Bangalore, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Indian Institute of Science, Bangalore, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5493,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79220779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"25","issue":"6","first_page":"1183","last_page":"1192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9789999723434448,"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/T10860","display_name":"Speech and Audio Processing","score":0.9742000102996826,"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/spectrogram","display_name":"Spectrogram","score":0.9553221464157104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6148823499679565},{"id":"https://openalex.org/keywords/binary-golay-code","display_name":"Binary Golay code","score":0.6016207337379456},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5649968385696411},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46449995040893555},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.4418472945690155},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.43056607246398926},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42064353823661804},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4151732325553894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39336249232292175},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.385386198759079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3779038190841675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36538898944854736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3228986859321594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20079496502876282},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1562596559524536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1282602846622467},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1004146933555603},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09313198924064636}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9553221464157104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6148823499679565},{"id":"https://openalex.org/C165293857","wikidata":"https://www.wikidata.org/wiki/Q1534522","display_name":"Binary Golay code","level":2,"score":0.6016207337379456},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5649968385696411},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46449995040893555},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.4418472945690155},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.43056607246398926},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42064353823661804},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4151732325553894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39336249232292175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.385386198759079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3779038190841675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36538898944854736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3228986859321594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20079496502876282},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1562596559524536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1282602846622467},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1004146933555603},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09313198924064636},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2690562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690562","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai::73400","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/73400/1/MPRA_paper_73400.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai::73400","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/73400/1/MPRA_paper_73400.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2620221678.pdf","grobid_xml":"https://content.openalex.org/works/W2620221678.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W349459512","https://openalex.org/W1066076866","https://openalex.org/W1965677444","https://openalex.org/W1967818247","https://openalex.org/W1968027146","https://openalex.org/W1986315484","https://openalex.org/W2002850343","https://openalex.org/W2003212690","https://openalex.org/W2010122185","https://openalex.org/W2013969548","https://openalex.org/W2028335839","https://openalex.org/W2030764705","https://openalex.org/W2045486043","https://openalex.org/W2048542643","https://openalex.org/W2061329611","https://openalex.org/W2072814159","https://openalex.org/W2085409940","https://openalex.org/W2086908954","https://openalex.org/W2088328344","https://openalex.org/W2109606373","https://openalex.org/W2111751070","https://openalex.org/W2115891142","https://openalex.org/W2122979854","https://openalex.org/W2127135195","https://openalex.org/W2145340043","https://openalex.org/W2149241068","https://openalex.org/W2149507322","https://openalex.org/W2150823344","https://openalex.org/W2158642611","https://openalex.org/W2174889280","https://openalex.org/W2189499810","https://openalex.org/W2222417652","https://openalex.org/W2282163567","https://openalex.org/W2293488548","https://openalex.org/W2401329062","https://openalex.org/W2467029522","https://openalex.org/W3015219919","https://openalex.org/W3102166770"],"related_works":["https://openalex.org/W3170167497","https://openalex.org/W2089315226","https://openalex.org/W4252208810","https://openalex.org/W1975881626","https://openalex.org/W2942893872","https://openalex.org/W2006097237","https://openalex.org/W4386758235","https://openalex.org/W2470608223","https://openalex.org/W2249987663","https://openalex.org/W2065606036"],"abstract_inverted_index":{"Bird":[0],"sound":[1,33,130,185,222],"detection":[2,34],"from":[3,27,116,172],"real-field":[4],"recordings":[5],"is":[6,60,78,91,214],"essential":[7],"for":[8,128,220],"identifying":[9],"bird":[10,32,94,129,184,221],"species":[11],"in":[12,16,99,113,120,247],"bioacoustic":[13],"monitoring.":[14],"Variations":[15],"the":[17,23,31,53,72,100,117,121,125,148,156,166,195,217,227,239,242],"recording":[18,207],"devices,":[19],"environmental":[20],"conditions,":[21],"and":[22,80,208],"presence":[24],"of":[25,108,110,124,139,174,183,241],"vocalizations":[26],"other":[28],"animals":[29],"make":[30],"very":[35],"challenging.":[36],"In":[37,52,132],"order":[38],"to":[39,147,178,193,238],"overcome":[40],"these":[41,106,175],"challenges,":[42],"we":[43,135],"propose":[44,161],"an":[45],"unsupervised":[46],"algorithm":[47],"comprising":[48],"two":[49],"main":[50],"stages.":[51],"first":[54],"stage,":[55],"a":[56,63,137,162],"spectrogram":[57,73],"enhancement":[58],"technique":[59],"proposed":[61,126,228],"using":[62,75],"multiple":[64],"window":[65,88],"Savitzky-Golay":[66],"(MWSG)":[67],"filter.":[68],"We":[69,104,160,224],"show":[70],"that":[71,93,144,154,226],"estimate":[74],"MWSG":[76],"filter":[77],"unbiased":[79],"has":[81],"lower":[82],"variance":[83],"compared":[84,237],"with":[85,201,205],"its":[86],"single":[87],"counterpart.":[89],"It":[90],"known":[92],"sounds":[95],"are":[96,190,199],"highly":[97],"structured":[98],"time-frequency":[101],"(T-F)":[102],"plane.":[103],"exploit":[105],"cues":[107],"prominence":[109],"T-F":[111],"activity":[112],"specific":[114,158],"directions":[115],"enhanced":[118,149],"spectrogram,":[119,150],"second":[122],"stage":[123],"method,":[127,229],"detection.":[131,223],"this":[133,248],"regard,":[134],"use":[136],"set":[138],"four":[140],"moving":[141],"average":[142],"filters":[143],"when":[145],"applied":[146],"yield":[151],"directional":[152,176],"spectrograms":[153,177],"capture":[155],"direction":[157],"information.":[159],"thresholding":[163],"scheme":[164],"on":[165,230],"time":[167],"varying":[168,206],"energy":[169],"profile":[170],"computed":[171],"each":[173],"obtain":[179,194],"frame-level":[180],"binary":[181],"decisions":[182,189],"activity.":[186],"These":[187],"individual":[188],"then":[191],"combined":[192],"final":[196],"decision.":[197],"Experiments":[198],"performed":[200],"three":[202],"different":[203],"datasets,":[204],"noise":[209],"conditions.":[210],"Frame":[211],"level":[212],"F-score":[213,234],"used":[215],"as":[216],"evaluation":[218],"metric":[219],"find":[225],"average,":[231],"achieves":[232],"higher":[233],"($10.24\\%$":[235],"relative)":[236],"best":[240],"six":[243],"baseline":[244],"schemes":[245],"considered":[246],"work.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
