{"id":"https://openalex.org/W4226048476","doi":"https://doi.org/10.1109/taslp.2022.3155285","title":"Segmentation of Multitalker Mixtures Based on Local Feature Contrasts and Auditory Glimpses","display_name":"Segmentation of Multitalker Mixtures Based on Local Feature Contrasts and Auditory Glimpses","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226048476","doi":"https://doi.org/10.1109/taslp.2022.3155285"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3155285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3155285","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://orbit.dtu.dk/en/publications/5f0a9698-a7e8-4390-a827-01ad8431f1cf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038645039","display_name":"Sarinah Sutojo","orcid":"https://orcid.org/0000-0001-7619-6132"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sarinah Sutojo","raw_affiliation_strings":["Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4All, Carl von Ossietzky University of Oldenburg, Oldenburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7619-6132","affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4All, Carl von Ossietzky University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-5463-5509","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005034522","display_name":"Steven van de Par","orcid":"https://orcid.org/0000-0002-3360-2011"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steven van de Par","raw_affiliation_strings":["Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4All, Carl von Ossietzky University of Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4All, Carl von Ossietzky University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03558217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1249","last_page":"1262"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7980678677558899},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.7001803517341614},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.695313572883606},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6724421977996826},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6702837944030762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6619046926498413},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5841960906982422},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4878287613391876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4757504165172577},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45101362466812134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43902382254600525},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4245331287384033},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.4201188087463379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4013598561286926},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15638461709022522},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14796552062034607},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09648957848548889},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09307438135147095}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7980678677558899},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.7001803517341614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.695313572883606},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6724421977996826},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6702837944030762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6619046926498413},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5841960906982422},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4878287613391876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4757504165172577},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45101362466812134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43902382254600525},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4245331287384033},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.4201188087463379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4013598561286926},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15638461709022522},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14796552062034607},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09648957848548889},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09307438135147095},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3155285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3155285","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:pure.atira.dk:publications/5f0a9698-a7e8-4390-a827-01ad8431f1cf","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/5f0a9698-a7e8-4390-a827-01ad8431f1cf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sutojo , S , May , T &amp; Van de Par , S 2022 , ' Segmentation of Multitalker Mixtures Based on Local Feature Contrasts and Auditory Glimpses ' , IEEE/ACM Transactions on Audio, Speech, and Language Processing , vol. 30 , pp. 1249-1262 . https://doi.org/10.1109/TASLP.2022.3155285","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/5f0a9698-a7e8-4390-a827-01ad8431f1cf","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/5f0a9698-a7e8-4390-a827-01ad8431f1cf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sutojo , S , May , T &amp; Van de Par , S 2022 , ' Segmentation of Multitalker Mixtures Based on Local Feature Contrasts and Auditory Glimpses ' , IEEE/ACM Transactions on Audio, Speech, and Language Processing , vol. 30 , pp. 1249-1262 . https://doi.org/10.1109/TASLP.2022.3155285","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G1331233524","display_name":null,"funder_award_id":"INST 184/157-1 FUGG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3825870578","display_name":"SFB 1330: H\u00f6rakustik: Perzeptive Prinzipien, Algorithmen und Anwendungen","funder_award_id":"352015383","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5712227735","display_name":null,"funder_award_id":"184/157-1 FUGG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6246985505","display_name":null,"funder_award_id":"352015383 SFB 1330 B2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7238242471","display_name":null,"funder_award_id":"SFB 1330 B2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7821612097","display_name":null,"funder_award_id":"SFB 1330","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7890451707","display_name":null,"funder_award_id":"184/157-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W190004713","https://openalex.org/W1550021044","https://openalex.org/W1967148872","https://openalex.org/W1979815907","https://openalex.org/W1989954041","https://openalex.org/W1999478155","https://openalex.org/W2014894389","https://openalex.org/W2044222806","https://openalex.org/W2047919706","https://openalex.org/W2050758723","https://openalex.org/W2060741034","https://openalex.org/W2069681747","https://openalex.org/W2072184010","https://openalex.org/W2074022644","https://openalex.org/W2075076415","https://openalex.org/W2088361146","https://openalex.org/W2095705004","https://openalex.org/W2101616935","https://openalex.org/W2106603795","https://openalex.org/W2106746989","https://openalex.org/W2108502666","https://openalex.org/W2124149378","https://openalex.org/W2140676414","https://openalex.org/W2141411743","https://openalex.org/W2143027228","https://openalex.org/W2144763279","https://openalex.org/W2166682639","https://openalex.org/W2166817508","https://openalex.org/W2171000037","https://openalex.org/W2221409856","https://openalex.org/W2291372403","https://openalex.org/W2558649592","https://openalex.org/W2562016190","https://openalex.org/W2622055663","https://openalex.org/W2734774145","https://openalex.org/W2755550219","https://openalex.org/W2765962757","https://openalex.org/W2804382237","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2917839452","https://openalex.org/W2998657200","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W3006474185","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W2043380045"],"abstract_inverted_index":{"The":[0],"separation":[1,30],"of":[2,11,18,28,38,45,81,124,202,232],"unknown":[3],"sources":[4],"from":[5],"an":[6,54],"acoustic":[7,82,137],"scene":[8],"remains":[9],"one":[10],"the":[12,16,26,39,43,49,61,77,115,128,144,155,174,195,200,208,218,230,233],"main":[13],"challenges":[14],"in":[15,31,48,71,236,238],"analysis":[17,44],"audio":[19],"signals.":[20],"In":[21,60],"this":[22],"paper":[23],"we":[24],"address":[25],"problem":[27],"source":[29,126,190,209],"multitalker":[32],"scenarios,":[33],"attempting":[34],"a":[35,72,203],"speaker-independent":[36],"segmentation":[37,175,221],"scene,":[40],"based":[41,211,220],"on":[42,212],"relative":[46,94,120],"changes":[47,96,122],"grouping":[50],"features,":[51],"followed":[52],"by":[53,114],"ideal":[55],"binary":[56],"mask":[57],"(IBM)":[58],"estimation.":[59],"presented":[62,129],"algorithm,":[63],"periodicity,":[64],"power,":[65],"and":[66,79,168,189,199,225],"spatial":[67,213],"features":[68,224],"are":[69,102,112,147],"combined":[70],"general":[73],"framework":[74],"to":[75,92,104,135,150,164,179,185],"estimate":[76],"on-":[78],"offsets":[80],"sources.":[83],"A":[84,159,192],"deep":[85],"neural":[86],"network":[87],"(DNN)":[88],"is":[89,132],"then":[90,148],"applied":[91],"convert":[93],"feature":[95,121],"into":[97],"spectro-temporal":[98,109,226],"contrast":[99,219],"maps":[100],"which":[101,111,206],"used":[103],"extract":[105],"auditory":[106],"glimpses,":[107],"i.e.":[108],"segments":[110],"dominated":[113],"same":[116],"source.":[117],"By":[118],"exploiting":[119],"instead":[123],"absolute":[125],"properties,":[127],"glimpse":[130],"formation":[131],"well":[133,178,183],"applicable":[134],"unseen":[136,180],"conditions":[138,188,239],"or":[139],"speakers.":[140],"Using":[141],"retrospective":[142],"labeling,":[143],"formed":[145],"glimpses":[146],"assigned":[149],"fixed":[151],"azimuth":[152],"locations,":[153],"providing":[154],"final":[156,196],"IBM":[157,197],"estimate.":[158],"systematic":[160],"evaluation":[161],"with":[162,240],"up":[163],"five":[165],"competing":[166],"speakers":[167,181],"interfering":[169,242],"diffuse":[170],"noise":[171,187],"shows":[172,216],"that":[173,217],"procedure":[176],"generalizes":[177],"as":[182,184],"untrained":[186],"numbers.":[191],"comparison":[193],"between":[194],"estimates":[198],"output":[201],"baseline":[204],"system,":[205],"performs":[207],"segregation":[210],"cues":[214],"only,":[215],"utilizing":[222],"multiple":[223,241],"context":[227],"can":[228],"improve":[229],"quality":[231],"estimated":[234],"IBMs,":[235],"particular":[237],"talkers.":[243]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
