{"id":"https://openalex.org/W2718701456","doi":"https://doi.org/10.1109/icassp.2017.7953191","title":"Robust speaker recognition based on DNN/i-vectors and speech separation","display_name":"Robust speaker recognition based on DNN/i-vectors and speech separation","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2718701456","doi":"https://doi.org/10.1109/icassp.2017.7953191","mag":"2718701456"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029447474","display_name":"Jorge Chang","orcid":"https://orcid.org/0000-0002-9289-4480"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jorge Chang","raw_affiliation_strings":["Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029447474"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.808,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96122266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5415","last_page":"5419"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.8147897720336914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617632150650024},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6490281224250793},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5785760879516602},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5074464678764343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49521151185035706},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49469348788261414},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4926906228065491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4620271325111389},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21727117896080017}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8147897720336914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617632150650024},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6490281224250793},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5785760879516602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5074464678764343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49521151185035706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49469348788261414},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4926906228065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4620271325111389},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21727117896080017},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1524333225","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2055611715","https://openalex.org/W2057826000","https://openalex.org/W2069681747","https://openalex.org/W2078169166","https://openalex.org/W2145846419","https://openalex.org/W2146502635","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2291877678","https://openalex.org/W2296167893","https://openalex.org/W2344822617","https://openalex.org/W2364134690","https://openalex.org/W2962751625","https://openalex.org/W2963068250","https://openalex.org/W4234330420","https://openalex.org/W6608353291","https://openalex.org/W6631362777","https://openalex.org/W6664675605","https://openalex.org/W6681435938","https://openalex.org/W6704529918"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"Recent":[0],"research":[1],"shows":[2],"that":[3],"the":[4,78,104,109,123,128],"i-vector":[5,67,124,140],"framework":[6],"for":[7,28,89,122],"speaker":[8,59],"recognition":[9,31,60],"can":[10],"significantly":[11],"benefit":[12],"from":[13],"phonetic":[14],"information.":[15],"A":[16],"common":[17],"approach":[18],"is":[19,54,115],"to":[20,32,56,76,102,118],"use":[21],"a":[22,34,65,74,100,132,137],"deep":[23],"neural":[24],"network":[25],"(DNN)":[26],"trained":[27,134],"automatic":[29],"speech":[30,83,114],"generate":[33],"universal":[35],"background":[36,52],"model":[37],"(UBM).":[38],"Studies":[39],"in":[40,46,69,152,157],"this":[41],"area":[42],"have":[43],"been":[44],"done":[45],"relatively":[47],"clean":[48],"conditions.":[49,71],"However,":[50],"strong":[51],"noise":[53,79],"known":[55],"severely":[57],"reduce":[58],"performance.":[61],"This":[62],"study":[63],"investigates":[64],"phonetically-aware":[66],"system":[68,98,130,144],"noisy":[70,110],"We":[72,126],"propose":[73],"front-end":[75],"tackle":[77],"problem":[80],"by":[81],"performing":[82],"separation":[84,97],"and":[85,92,136,155],"examine":[86],"its":[87],"performance":[88],"both":[90],"verification":[91],"identification":[93,153],"tasks.":[94],"The":[95,112],"proposed":[96,129,143],"trains":[99],"DNN":[101],"estimate":[103],"ideal":[105],"ratio":[106],"mask":[107],"of":[108,150],"speech.":[111],"separated":[113],"then":[116],"used":[117],"extract":[119],"enhanced":[120],"features":[121],"framework.":[125],"compare":[127],"against":[131],"multi-condition":[133],"baseline":[135],"traditional":[138],"GMM-UBM":[139],"system.":[141],"Our":[142],"provides":[145],"an":[146],"absolute":[147],"average":[148],"improvement":[149],"8%":[151],"accuracy":[154],"1.2%":[156],"equal":[158],"error":[159],"rate.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-23T05:10:03.516525","created_date":"2025-10-10T00:00:00"}