{"id":"https://openalex.org/W2745074882","doi":"https://doi.org/10.1109/hsi.2017.8004991","title":"Playback detection using machine learning with spectrogram features approach","display_name":"Playback detection using machine learning with spectrogram features approach","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2745074882","doi":"https://doi.org/10.1109/hsi.2017.8004991","mag":"2745074882"},"language":"en","primary_location":{"id":"doi:10.1109/hsi.2017.8004991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi.2017.8004991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 10th International Conference on Human System Interactions (HSI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001808007","display_name":"Jerzy Dembski","orcid":"https://orcid.org/0000-0002-6011-1955"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jerzy Dembski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Gda\u0144sk University of Technology, Gda\u0144sk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Gda\u0144sk University of Technology, Gda\u0144sk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044309467","display_name":"Jacek Rumi\u0144ski","orcid":"https://orcid.org/0000-0003-2266-0088"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jacek Ruminski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Gda\u0144sk University of Technology, Gda\u0144sk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Gda\u0144sk University of Technology, Gda\u0144sk, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169333911"],"apc_list":null,"apc_paid":null,"fwci":0.1384,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41606915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"57","issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.6806156039237976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6772099137306213},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6731375455856323},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.653110921382904},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6021616458892822},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5885926485061646},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5296167135238647},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.4797062277793884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4708395004272461},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4678068459033966},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.437593013048172},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4246731698513031},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1791459321975708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6806156039237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6772099137306213},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6731375455856323},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.653110921382904},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6021616458892822},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5885926485061646},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5296167135238647},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.4797062277793884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4708395004272461},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4678068459033966},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.437593013048172},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4246731698513031},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1791459321975708},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hsi.2017.8004991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hsi.2017.8004991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 10th International Conference on Human System Interactions (HSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1550352777","https://openalex.org/W1975846642","https://openalex.org/W1980581462","https://openalex.org/W2062703747","https://openalex.org/W2083458151","https://openalex.org/W2109740207","https://openalex.org/W2114376863","https://openalex.org/W2117052143","https://openalex.org/W2124386111","https://openalex.org/W2153635508","https://openalex.org/W2161969291","https://openalex.org/W2402156731","https://openalex.org/W2610995940","https://openalex.org/W3097096317","https://openalex.org/W4239510810","https://openalex.org/W6677660597","https://openalex.org/W6713239009","https://openalex.org/W6737357404"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"2D":[3],"image":[4],"processing":[5],"approach":[6],"to":[7],"playback":[8,60,73,144],"detection":[9,74,145],"in":[10,55,67,111,118,147,150],"automatic":[11],"speaker":[12],"verification":[13],"(ASV)":[14],"systems":[15,75],"using":[16],"spectrograms":[17],"as":[18],"speech":[19,82],"signal":[20],"representation.":[21],"Three":[22],"feature":[23],"extraction":[24],"and":[25,43,69,78,105,126],"classification":[26],"methods:":[27],"histograms":[28],"of":[29,57,101],"oriented":[30],"gradients":[31],"(HOG)":[32],"with":[33,40,64],"support":[34],"vector":[35],"machines":[36],"(SVM),":[37],"HAAR":[38],"wavelets":[39],"AdaBoost":[41],"classifier":[42],"deep":[44],"convolutional":[45],"neural":[46],"networks":[47],"(CNN)":[48],"were":[49,76,134],"compared":[50],"on":[51,80],"different":[52,65,89,151],"data":[53],"partitions":[54],"respect":[56],"speakers":[58,66],"or":[59],"devices:":[61],"for":[62,94,103,109,124,129,143],"instance":[63],"training":[68,125],"test":[70,92,131],"subsets.":[71],"The":[72,91],"trained":[77],"tested":[79],"two":[81,88],"datasets":[83,96],"S1and":[84],"S2manufactured":[85],"independently":[86],"by":[87],"institutions.":[90],"error":[93],"both":[95],"oscillates":[97],"about":[98],"the":[99,130,132,140],"level":[100],"1%":[102],"HOG+SVM":[104],"even":[106],"below":[107],"it":[108],"CNN":[110],"bigger":[112],"S1base.":[113],"In":[114],"cross":[115],"validation":[116],"scenario":[117],"which":[119],"one":[120],"base":[121,128,149],"was":[122],"used":[123],"second":[127],"results":[133],"very":[135],"poor":[136],"what":[137],"suggests":[138],"that":[139],"information":[141],"relevant":[142],"appeared":[146],"each":[148],"way.":[152]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}