{"id":"https://openalex.org/W3038555974","doi":"https://doi.org/10.1587/transinf.2019edp7259","title":"A Two-Stage Phase-Aware Approach for Monaural Multi-Talker Speech Separation","display_name":"A Two-Stage Phase-Aware Approach for Monaural Multi-Talker Speech Separation","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3038555974","doi":"https://doi.org/10.1587/transinf.2019edp7259","mag":"3038555974"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7259","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7259","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/7/E103.D_2019EDP7259/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/7/E103.D_2019EDP7259/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039943423","display_name":"Yin Lu","orcid":"https://orcid.org/0000-0002-9568-7428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu YIN","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450058","display_name":"Junfeng Li","orcid":"https://orcid.org/0000-0002-6272-9169"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng LI","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong YAN","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","University of Chinese Academy of Sciences","Xinjiang Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Xinjiang Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato AKAGI","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1485,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4140625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E103.D","issue":"7","first_page":"1732","last_page":"1743"},"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":0.9983000159263611,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9509376883506775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8507822155952454},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6486830711364746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5768963098526001},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45253899693489075},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.45226091146469116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4055025279521942},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33055245876312256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18856710195541382},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.056482404470443726},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05232053995132446}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9509376883506775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507822155952454},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6486830711364746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5768963098526001},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45253899693489075},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.45226091146469116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4055025279521942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33055245876312256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18856710195541382},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.056482404470443726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05232053995132446},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1587/transinf.2019edp7259","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7259","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/7/E103.D_2019EDP7259/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0004537814","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/16673","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions Information and Systems","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7259","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7259","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/7/E103.D_2019EDP7259/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038555974.pdf","grobid_xml":"https://content.openalex.org/works/W3038555974.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1536373746","https://openalex.org/W1555814299","https://openalex.org/W1635512741","https://openalex.org/W1800365115","https://openalex.org/W1805162375","https://openalex.org/W1902027874","https://openalex.org/W2024351659","https://openalex.org/W2031647436","https://openalex.org/W2041498927","https://openalex.org/W2046869671","https://openalex.org/W2048142341","https://openalex.org/W2050112415","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2072184010","https://openalex.org/W2079756844","https://openalex.org/W2093214668","https://openalex.org/W2095705004","https://openalex.org/W2101304342","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2130476329","https://openalex.org/W2141411743","https://openalex.org/W2144763279","https://openalex.org/W2155531311","https://openalex.org/W2156379660","https://openalex.org/W2161863519","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2402466562","https://openalex.org/W2405589348","https://openalex.org/W2406737436","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2578331995","https://openalex.org/W2599685671","https://openalex.org/W2734774145","https://openalex.org/W2874689226","https://openalex.org/W2889134433","https://openalex.org/W2889206679","https://openalex.org/W2889597349","https://openalex.org/W2891405874","https://openalex.org/W2894785362","https://openalex.org/W2900132857","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963189033","https://openalex.org/W2963317762","https://openalex.org/W2964121744","https://openalex.org/W3099330747","https://openalex.org/W3147539069"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2401567014","https://openalex.org/W2889698889"],"abstract_inverted_index":{"The":[0,44,97,152,195],"simultaneous":[1],"utterances":[2],"impact":[3],"the":[4,8,23,33,38,47,72,77,80,100,105,110,116,120,133,140,149,155,165,168,179,183,187,192,200,205,208],"ability":[5],"of":[6,46,135,173,191,207],"both":[7],"hearing-impaired":[9],"persons":[10],"and":[11,36,95,107,138,154,167,189],"automatic":[12],"speech":[13,24,34,42,67],"recognition":[14],"systems.":[15],"Recently,":[16],"deep":[17],"neural":[18,174],"networks":[19],"have":[20],"dramatically":[21],"improved":[22],"separation":[25,56],"performance.":[26,57],"However,":[27],"most":[28],"previous":[29],"works":[30],"only":[31],"estimate":[32],"magnitude":[35,73,150,180],"use":[37,45],"mixture":[39,48],"phase":[40,49,81,123,128,136,166],"for":[41,55,65,119,132,148,178],"reconstruction.":[43],"has":[50],"become":[51],"a":[52,61],"critical":[53],"limitation":[54],"This":[58],"study":[59,98],"proposes":[60],"two-stage":[62],"phase-aware":[63],"approach":[64,202],"multi-talker":[66],"separation,":[68],"which":[69,125],"integrally":[70],"recovers":[71],"as":[74,76],"well":[75],"phase.":[78],"For":[79],"recovery,":[82,124],"Multiple":[83],"Input":[84],"Spectrogram":[85],"Inversion":[86],"(MISI)":[87],"algorithm":[88,102],"is":[89,115,146],"utilized":[90],"due":[91],"to":[92,163],"its":[93],"effectiveness":[94,188],"simplicity.":[96],"implements":[99],"MISI":[101,122],"based":[103],"on":[104,182],"mask":[106,113,118,145,157],"gives":[108],"that":[109,199],"ideal":[111],"amplitude":[112],"(IAM)":[114],"optimal":[117],"mask-based":[121],"brings":[126],"less":[127],"distortion.":[129],"To":[130],"compensate":[131],"error":[134],"recovery":[137],"minimize":[139],"signal":[141],"distortion,":[142],"an":[143],"advanced":[144],"proposed":[147,156,193,201],"estimation.":[151],"IAM":[153],"are":[158,176],"estimated":[159],"at":[160],"different":[161],"stages":[162],"recover":[164],"magnitude,":[169],"respectively.":[170],"Two":[171],"frameworks":[172],"network":[175],"evaluated":[177],"estimation":[181],"second":[184],"stage,":[185],"demonstrating":[186],"flexibility":[190],"approach.":[194],"experimental":[196],"results":[197],"demonstrate":[198],"significantly":[203],"minimizes":[204],"distortions":[206],"separated":[209],"speech.":[210]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
