{"id":"https://openalex.org/W2062470372","doi":"https://doi.org/10.1109/icassp.2010.5495590","title":"Speaker identification with distant microphone speech","display_name":"Speaker identification with distant microphone speech","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2062470372","doi":"https://doi.org/10.1109/icassp.2010.5495590","mag":"2062470372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036810731","display_name":"Runxin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runxin Li","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428618","display_name":"Qian Yang","orcid":"https://orcid.org/0000-0002-6552-7482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Yang","raw_affiliation_strings":["Fakult\u00e4t f\u00fcr Informatik, Universit\u00e4t Karlsruhe, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t f\u00fcr Informatik, Universit\u00e4t Karlsruhe, Karlsruhe, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030859194","display_name":"Kornel Laskowski","orcid":"https://orcid.org/0009-0008-8060-6913"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kornel Laskowski","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["Fakult\u00e4t f\u00fcr Informatik, Universit\u00e4t Karlsruhe, Karlsruhe, Germany","Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t f\u00fcr Informatik, Universit\u00e4t Karlsruhe, Karlsruhe, Germany","institution_ids":[]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"4518","last_page":"4521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9927999973297119,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8916082978248596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7739579677581787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7493515014648438},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6730791926383972},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5668818354606628},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5343448519706726},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5272974967956543},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5257837772369385},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.503431499004364},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4971807301044464},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4691912829875946},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4605092406272888},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4480205774307251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42699721455574036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4240674674510956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12480118870735168},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05943211913108826}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8916082978248596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7739579677581787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493515014648438},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6730791926383972},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5668818354606628},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5343448519706726},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5272974967956543},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5257837772369385},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.503431499004364},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4971807301044464},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4691912829875946},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4605092406272888},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4480205774307251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42699721455574036},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4240674674510956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12480118870735168},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05943211913108826},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.1231","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.1231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~kornel/pubs/0004518.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W180973252","https://openalex.org/W322227076","https://openalex.org/W1532958172","https://openalex.org/W1588533203","https://openalex.org/W1758836951","https://openalex.org/W2040266692","https://openalex.org/W2041823554","https://openalex.org/W2053150333","https://openalex.org/W2103069945","https://openalex.org/W2109449312","https://openalex.org/W2121750345","https://openalex.org/W2136105097","https://openalex.org/W2139737683","https://openalex.org/W2159591770","https://openalex.org/W2404921859","https://openalex.org/W4246960037","https://openalex.org/W6607322422","https://openalex.org/W6676548200","https://openalex.org/W6713136263"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,25,45],"speaker":[3,48],"identification":[4],"has":[5],"recently":[6],"seen":[7],"significant":[8],"advancement,":[9],"but":[10],"improvements":[11],"have":[12],"tended":[13],"to":[14,79,97],"be":[15],"benchmarked":[16],"on":[17,35],"near-field":[18],"speech,":[19],"ignoring":[20],"the":[21,39,43,98],"more":[22,99],"realistic":[23],"setting":[24],"far-field-instrumented":[26],"speakers.":[27],"In":[28],"this":[29],"work":[30],"we":[31,55,86,104],"present":[32,87],"several":[33],"findings":[34],"far-field":[36],"speech":[37],"from":[38],"MIXER5":[40],"Corpus,":[41],"in":[42],"areas":[44],"feature":[46],"extraction,":[47],"modeling,":[49],"and":[50,69,82],"multichannel":[51],"score":[52,108],"combination.":[53],"First,":[54],"observe":[56],"that":[57,70,89,106],"minimum-variance":[58],"distortionless":[59],"response":[60],"(MVDR)":[61],"features":[62,75],"outperform":[63],"Mel-frequency":[64],"cepstral":[65],"coefficient":[66],"(MFCC)":[67],"features,":[68],"fundamental":[71],"frequency":[72],"variation":[73],"(FFV)":[74],"offer":[76],"complimentary":[77],"information":[78],"both":[80],"MFCC":[81],"MVDR":[83],"features.":[84],"Second,":[85],"evidence":[88],"factor":[90],"analysis":[91],"significantly":[92,110],"improves":[93,111],"system":[94],"performance,":[95],"compared":[96],"traditional":[100],"GMM/UBM":[101],"strategy.":[102],"Third,":[103],"find":[105],"frame-based":[107],"competition":[109],"performance":[112],"under":[113],"mismatched":[114],"conditions":[115],"with":[116],"multiple":[117],"channels":[118],"available.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}