{"id":"https://openalex.org/W2946642761","doi":"https://doi.org/10.1145/3318299.3318386","title":"Evaluating Acoustic Feature Maps in 2D-CNN for Speaker Identification","display_name":"Evaluating Acoustic Feature Maps in 2D-CNN for Speaker Identification","publication_year":2019,"publication_date":"2019-02-22","ids":{"openalex":"https://openalex.org/W2946642761","doi":"https://doi.org/10.1145/3318299.3318386","mag":"2946642761"},"language":"en","primary_location":{"id":"doi:10.1145/3318299.3318386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318299.3318386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 11th International Conference on Machine Learning and Computing","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/A5044015235","display_name":"Ali Shariq Imran","orcid":"https://orcid.org/0000-0002-2416-2878"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Ali Shariq Imran","raw_affiliation_strings":["Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087453842","display_name":"Vetle Haflan","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Vetle Haflan","raw_affiliation_strings":["Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032571112","display_name":"Abdolreza Sabzi Shahrebabaki","orcid":"https://orcid.org/0000-0002-0877-9456"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Abdolreza Sabzi Shahrebabaki","raw_affiliation_strings":["Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054931657","display_name":"Negar Olfati","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Negar Olfati","raw_affiliation_strings":["Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Karl Svendsen","raw_affiliation_strings":["Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Norwegian University of Science & Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044015235"],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54771871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.8386209011077881},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.831250786781311},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7896217703819275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6744155883789062},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.650375485420227},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6169250011444092},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5548344254493713},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5310671329498291},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5093823671340942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5068758130073547},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5056166648864746},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48575499653816223},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4656071960926056},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41605085134506226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386209011077881},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.831250786781311},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7896217703819275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6744155883789062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.650375485420227},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6169250011444092},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5548344254493713},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5310671329498291},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5093823671340942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5068758130073547},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5056166648864746},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48575499653816223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4656071960926056},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41605085134506226},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3318299.3318386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318299.3318386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 11th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1578856370","https://openalex.org/W1995562189","https://openalex.org/W2088382258","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2170065313","https://openalex.org/W2193413348","https://openalex.org/W2549349626","https://openalex.org/W2612399879","https://openalex.org/W2726515241","https://openalex.org/W6600605178"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2185075503"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51,63,165],"study":[4],"evaluating":[5],"different":[6,121],"acoustic":[7,122,186],"feature":[8,33,81,127],"map":[9,82,128],"representations":[10,129],"in":[11,55,115,132],"two-dimensional":[12],"convolutional":[13],"neural":[14],"networks":[15],"(2D-CNN)":[16],"on":[17,137,164],"the":[18,26,96,184],"speech":[19,139],"dataset":[20],"for":[21,35,66,104],"various":[22],"speech-related":[23],"activities.":[24],"Specifically,":[25],"task":[27],"involves":[28],"identifying":[29],"useful":[30],"2D-CNN":[31],"input":[32,80],"maps":[34],"enhancing":[36],"speaker":[37,45,106],"identification":[38],"with":[39,124],"an":[40,102,143],"ultimate":[41],"goal":[42],"to":[43,57,77,150],"improve":[44],"authentication":[46,107],"and":[47,59,156,174],"enabling":[48],"voice":[49,89,100],"as":[50,101],"biometric":[52],"feature.":[53],"Voice":[54],"contrast":[56],"fingerprints":[58],"image-based":[60],"biometrics":[61],"is":[62,180],"natural":[64],"choice":[65],"hands-free":[67],"communication":[68],"systems":[69],"where":[70],"touch":[71],"interfaces":[72],"are":[73,130],"inconvenient":[74],"or":[75],"dangerous":[76],"use.":[78],"Effective":[79],"representation":[83],"may":[84],"help":[85],"CNN":[86],"exploit":[87],"intrinsic":[88],"features":[90,123],"that":[91,142],"not":[92],"only":[93],"can":[94,112],"address":[95],"instability":[97],"issues":[98],"of":[99],"identifier":[103],"textindependent":[105],"while":[108],"preserving":[109],"privacy":[110],"but":[111],"also":[113],"assist":[114],"developing":[116],"efficacious":[117],"voice-enabled":[118],"interfaces.":[119],"Three":[120],"three":[125,138],"possible":[126],"evaluated":[131],"this":[133],"study.":[134],"Results":[135],"obtained":[136],"corpora":[140],"shows":[141],"interpolated":[144],"baseline":[145],"spectrogram":[146,178],"performs":[147],"best":[148],"compared":[149],"Mel":[151,157],"frequency":[152,158],"spectral":[153],"coefficients":[154],"(MFSC)":[155],"cepstral":[159],"coefficient":[160],"(MFCC)":[161],"when":[162],"tested":[163],"5-fold":[166],"cross-validation":[167],"method":[168],"using":[169],"2D-CNN.":[170],"On":[171],"both":[172],"textdependent":[173],"text-independent":[175],"datasets,":[176],"raw":[177],"accuracy":[179],"4%":[181],"better":[182],"than":[183],"traditional":[185],"features.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}