{"id":"https://openalex.org/W3029444444","doi":"https://doi.org/10.1145/3386415.3386968","title":"Monaural Speech Separation of Specific Speaker Based on Deep Learning","display_name":"Monaural Speech Separation of Specific Speaker Based on Deep Learning","publication_year":2019,"publication_date":"2019-12-06","ids":{"openalex":"https://openalex.org/W3029444444","doi":"https://doi.org/10.1145/3386415.3386968","mag":"3029444444"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386415.3386968","pdf_url":null,"source":{"id":"https://openalex.org/S4306523750","display_name":"Proceedings of the 2nd International Conference on Information Technologies and Electrical Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5037162594","display_name":"Yixuan Zhang","orcid":"https://orcid.org/0000-0002-7412-4669"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Zhang","raw_affiliation_strings":["School of Electronic Engineering, Guangxi Normal University, Guilin China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Guangxi Normal University, Guilin China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026477717","display_name":"Weiping Hu","orcid":"https://orcid.org/0000-0002-3567-6516"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Hu","raw_affiliation_strings":["School of Electronic Engineering, Guangxi Normal University, Guilin China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Guangxi Normal University, Guilin China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067288409","display_name":"Liting Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liting Chen","raw_affiliation_strings":["School of Electronic Engineering, Guangxi Normal University, Guilin China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Guangxi Normal University, Guilin China","institution_ids":["https://openalex.org/I29739308"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.142,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.236018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":61,"max":69},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9999,"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":0.9999,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9957,"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":0.9947,"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/robustness","display_name":"Robustness","score":0.67262703},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6539967},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5049599},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source Separation","score":0.496553},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42583793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904359},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7549014},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.67262703},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6539967},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5213369},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5049599},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.496553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44879663},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.438247},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4293004},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42583793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19916847},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386415.3386968","pdf_url":null,"source":{"id":"https://openalex.org/S4306523750","display_name":"Proceedings of the 2nd International Conference on Information Technologies and Electrical Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":5,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W2086725969","https://openalex.org/W2304609584","https://openalex.org/W2345067732","https://openalex.org/W2902808043"],"related_works":["https://openalex.org/W4247736853","https://openalex.org/W2206035908","https://openalex.org/W2175373321","https://openalex.org/W2162158162","https://openalex.org/W2125642021","https://openalex.org/W2103031592","https://openalex.org/W1999004162","https://openalex.org/W1967226023","https://openalex.org/W178436704","https://openalex.org/W1493012537"],"abstract_inverted_index":{"The":[0,35,52,143,184],"traditional":[1],"speaker":[2,37,42,65,77,93,103],"separation":[3,28,119,182,190],"system":[4],"is":[5,14,33,39,88,192,200],"usually":[6],"only":[7],"for":[8,30],"two":[9],"speakers":[10,32,80],"to":[11,16,18,46,81],"separate,":[12],"which":[13,70],"difficult":[15],"apply":[17],"other":[19,79,95],"mixed":[20,89],"speech.":[21],"In":[22,161],"this":[23,163],"paper,":[24],"a":[25],"mono-channel":[26],"speech":[27,61,99],"method":[29],"specific":[31,36,64],"proposed.":[34],"here":[38],"the":[40,49,57,60,63,72,75,85,91,98,101,110,118,151,166,169,178,181,189,195],"target":[41,76,92,102],"that":[43,147,188],"we":[44],"want":[45],"separate":[47],"from":[48,56],"mono":[50],"channel.":[51],"training":[53],"data":[54,87],"comes":[55],"mixture":[58],"of":[59,62,100,121,124,168,171,197],"with":[66],"multiple":[67],"non-specific":[68,96],"speakers,":[69],"reduces":[71],"dependence":[73],"between":[74],"and":[78,94,109,137],"some":[82],"extent.":[83],"When":[84],"test":[86],"by":[90],"people,":[97],"can":[104],"also":[105],"be":[106],"separated":[107],"well,":[108],"model":[111],"has":[112,150],"certain":[113],"robustness.":[114],"This":[115],"paper":[116,164],"compares":[117],"performance":[120,153,191],"three":[122],"kinds":[123],"network":[125,149,179],"models":[126],"based":[127],"on":[128,180],"Recurrent":[129],"Neural":[130],"Network":[131],"(RNN),":[132],"Long-Short":[133,139],"Term":[134,140],"Memory":[135,141],"(LSTM)":[136],"Bidirectional":[138],"(Bi-LSTM).":[142],"experimental":[144,185],"results":[145,186],"show":[146,187],"Bi-LSTM":[148],"best":[152,193],"under":[154],"Blind":[155],"Source":[156],"Separation":[157],"Evaluation":[158],"(BBS":[159],"Eval).":[160],"addition,":[162],"explores":[165],"influence":[167],"number":[170,196],"consecutive":[172],"time-frequency":[173],"amplitude":[174],"frames":[175,199],"input":[176,198],"into":[177],"results.":[183],"when":[194],"10.":[201]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3029444444","counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-12T20:40:43.138359","created_date":"2020-06-05"}