{"id":"https://openalex.org/W4318427124","doi":"https://doi.org/10.1007/s10772-023-10023-2","title":"Speaker identification and localization using shuffled MFCC features and deep learning","display_name":"Speaker identification and localization using shuffled MFCC features and deep learning","publication_year":2023,"publication_date":"2023-01-29","ids":{"openalex":"https://openalex.org/W4318427124","doi":"https://doi.org/10.1007/s10772-023-10023-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-023-10023-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10023-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10023-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10023-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028312507","display_name":"Mahdi Barhoush","orcid":"https://orcid.org/0000-0002-3787-0662"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mahdi Barhoush","raw_affiliation_strings":["INDA, RWTH Aachen, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3787-0662","affiliations":[{"raw_affiliation_string":"INDA, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003503441","display_name":"Ahmed Hallawa","orcid":"https://orcid.org/0000-0003-3932-4873"},"institutions":[{"id":"https://openalex.org/I4210120689","display_name":"Universit\u00e4tsklinikum Aachen","ror":"https://ror.org/02gm5zw39","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210120689"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed Hallawa","raw_affiliation_strings":["Artificial Intelligence for Critical Care Lab, University Hospital Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence for Critical Care Lab, University Hospital Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I4210120689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072895220","display_name":"Anke Schmeink","orcid":"https://orcid.org/0000-0002-9929-2925"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anke Schmeink","raw_affiliation_strings":["INDA, RWTH Aachen, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INDA, RWTH Aachen, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028312507"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2780},"fwci":3.2132,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92761976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"26","issue":"1","first_page":"185","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.8899575471878052},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.884093165397644},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7054868936538696},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.666548490524292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6179265379905701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6079625487327576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5705362558364868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5447677969932556},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4969206154346466},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.48287561535835266},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4508804380893707},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4337083399295807},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4309881925582886},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4193112254142761},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4177376627922058},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41222256422042847},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.409917950630188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8899575471878052},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.884093165397644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7054868936538696},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.666548490524292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6179265379905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6079625487327576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5705362558364868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5447677969932556},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4969206154346466},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.48287561535835266},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4508804380893707},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4337083399295807},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4309881925582886},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4193112254142761},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4177376627922058},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41222256422042847},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.409917950630188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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:10.1007/s10772-023-10023-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10023-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10023-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-023-10023-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10023-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10023-2.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318427124.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W1992475611","https://openalex.org/W2044063703","https://openalex.org/W2044401533","https://openalex.org/W2095705004","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2117678320","https://openalex.org/W2398972335","https://openalex.org/W2485688913","https://openalex.org/W2509065397","https://openalex.org/W2726515241","https://openalex.org/W2746141152","https://openalex.org/W2768188490","https://openalex.org/W2799831802","https://openalex.org/W2884822476","https://openalex.org/W2885219692","https://openalex.org/W2897977894","https://openalex.org/W2902123591","https://openalex.org/W2946508582","https://openalex.org/W2964052309","https://openalex.org/W2964808434","https://openalex.org/W2982500554","https://openalex.org/W3015312544","https://openalex.org/W3015621653","https://openalex.org/W3023420897","https://openalex.org/W3026870722","https://openalex.org/W3090563986","https://openalex.org/W3092531824","https://openalex.org/W3095737053","https://openalex.org/W3098357269","https://openalex.org/W3118639295","https://openalex.org/W3126210765","https://openalex.org/W3132182240","https://openalex.org/W3133656786","https://openalex.org/W3156052130","https://openalex.org/W3171302872","https://openalex.org/W3197097128","https://openalex.org/W3207728800","https://openalex.org/W4210306221","https://openalex.org/W4210726472","https://openalex.org/W4220707304","https://openalex.org/W4224917914","https://openalex.org/W4239751208","https://openalex.org/W6631190155","https://openalex.org/W6745136726","https://openalex.org/W7071198948"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W4389082013","https://openalex.org/W4234190324","https://openalex.org/W2185075503","https://openalex.org/W4396668120","https://openalex.org/W2104528589","https://openalex.org/W2126085626","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872"],"abstract_inverted_index":{"Abstract":[0],"The":[1,153],"use":[2],"of":[3,25,34,131],"machine":[4],"learning":[5],"in":[6,41,83,162],"automatic":[7],"speaker":[8,79],"identification":[9,49,133],"and":[10,30,37,50,63,75,85,114,134,145,150,168,171],"localization":[11,51,135],"systems":[12],"has":[13],"recently":[14],"seen":[15],"significant":[16],"advances.":[17],"However,":[18],"this":[19,42,96],"progress":[20],"comes":[21],"at":[22,142],"the":[23,32,129,132,139,166],"cost":[24],"using":[26,100],"complex":[27],"models,":[28],"computations,":[29],"increasing":[31],"number":[33],"microphone":[35],"arrays":[36],"training":[38,177],"data.":[39,178],"Therefore,":[40],"work,":[43],"we":[44,98,127],"propose":[45,99],"a":[46,55,90,101],"new":[47,91,140],"end-to-end":[48],"model":[52,69,137],"based":[53,108],"on":[54,138],"simple":[56],"fully":[57],"connected":[58],"deep":[59],"neural":[60],"network":[61],"(FC-DNN)":[62],"just":[64],"two":[65],"input":[66],"microphones.":[67],"This":[68],"can":[70],"jointly":[71],"or":[72],"separately":[73],"localize":[74],"identify":[76],"an":[77],"active":[78],"with":[80,175],"high":[81,160],"accuracy":[82,161],"single":[84,149],"multi-speaker":[86,151],"scenarios":[87],"by":[88],"exploiting":[89],"data":[92],"augmentation":[93],"approach.":[94],"In":[95,121],"regard,":[97],"novel":[102],"Mel":[103],"Frequency":[104],"Cepstral":[105],"Coefficients":[106],"(MFCC)":[107],"feature":[109],"called":[110],"Shuffled":[111,118],"MFCC":[112,119],"(SHMFCC)":[113],"its":[115],"variant":[116],"Difference":[117],"(DSHMFCC).":[120],"order":[122],"to":[123],"test":[124],"our":[125,157],"approach,":[126],"analyzed":[128],"performance":[130],"proposed":[136],"features":[141],"different":[143],"noise":[144],"reverberation":[146],"conditions":[147],"for":[148],"scenarios.":[152],"results":[154],"show":[155],"that":[156],"approach":[158],"achieves":[159,172],"these":[163],"scenarios,":[164],"outperforms":[165],"baseline":[167],"conventional":[169],"methods,":[170],"robustness":[173],"even":[174],"small-sized":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}