{"id":"https://openalex.org/W2935846637","doi":"https://doi.org/10.1109/icassp.2019.8682429","title":"Furcax: End-to-end Monaural Speech Separation Based on Deep Gated (De)convolutional Neural Networks with Adversarial Example Training","display_name":"Furcax: End-to-end Monaural Speech Separation Based on Deep Gated (De)convolutional Neural Networks with Adversarial Example Training","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2935846637","doi":"https://doi.org/10.1109/icassp.2019.8682429","mag":"2935846637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018232553","display_name":"Ziqiang Shi","orcid":"https://orcid.org/0000-0002-3105-6213"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Shi","raw_affiliation_strings":["Fujitsu Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research and Development Center, Beijing, China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036978677","display_name":"Huibin Lin","orcid":"https://orcid.org/0000-0002-7774-7722"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huibin Lin","raw_affiliation_strings":["Fujitsu Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research and Development Center, Beijing, China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324301","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-4218-8008"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Fujitsu Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research and Development Center, Beijing, China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044324493","display_name":"Rujie Liu","orcid":"https://orcid.org/0000-0002-4992-7312"},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujie Liu","raw_affiliation_strings":["Fujitsu Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research and Development Center, Beijing, China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045667527","display_name":"Shoji Hayakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Hayakawa","raw_affiliation_strings":["Fujitsu Laboratories Ltd., Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Laboratories Ltd., Kawasaki, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.485,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89884062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6985","last_page":"6989"},"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":0.9993000030517578,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7729480266571045},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7686049938201904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7436769604682922},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6377647519111633},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6334460973739624},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6156311631202698},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.554155707359314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5132842063903809},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.488133043050766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3439231514930725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7729480266571045},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7686049938201904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7436769604682922},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6377647519111633},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6334460973739624},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6156311631202698},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.554155707359314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5132842063903809},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.488133043050766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3439231514930725}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W2088361146","https://openalex.org/W2099471712","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2157906748","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2567070169","https://openalex.org/W2593414223","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2800022361","https://openalex.org/W2800664709","https://openalex.org/W2891405874","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963341071","https://openalex.org/W2963970792","https://openalex.org/W3124972797","https://openalex.org/W4320013936","https://openalex.org/W6603255414","https://openalex.org/W6731370813","https://openalex.org/W6745149982"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W1543248128"],"abstract_inverted_index":{"Deep":[0],"gated":[1,24,79],"convolutional":[2,25],"networks":[3,26,82],"have":[4],"been":[5],"proved":[6],"to":[7,53,95,112,170],"be":[8],"very":[9],"effective":[10,67],"in":[11,27,36,122],"single":[12],"channel":[13],"speech":[14,73,142],"separation.":[15],"However":[16],"current":[17],"state-of-the-art":[18],"framework":[19],"often":[20],"considers":[21],"training":[22,126,133],"the":[23,86,108,114,136,140,145,151,152,174],"time-frequency":[28],"(TF)":[29],"domain.":[30],"Such":[31],"an":[32,55,63],"approach":[33,69],"will":[34],"result":[35],"limited":[37],"perceptual":[38],"score,":[39],"such":[40],"as":[41],"signal-to-distortion":[42],"ratio":[43],"(SDR)":[44],"upper":[45],"bound":[46],"of":[47,77,89],"separated":[48,97,141,166],"utterances":[49,167],"and":[50,66,92,168],"also":[51],"fail":[52],"exploit":[54],"end-to-end":[56,68],"framework.":[57],"In":[58],"this":[59,159],"paper":[60],"we":[61,110],"present":[62],"integrated":[64],"simple":[65],"called":[70],"FurcaX1to":[71],"monaural":[72],"separation,":[74],"which":[75,138],"consists":[76],"deep":[78],"(de)convolutional":[80],"neural":[81],"(GCNN)":[83],"that":[84,158],"takes":[85],"mixed":[87],"utterance":[88,101,119],"two":[90,96],"speakers":[91],"maps":[93],"it":[94],"utterances,":[98],"where":[99],"each":[100],"contains":[102],"only":[103],"one":[104],"speaker's":[105],"voice.":[106],"For":[107],"objective,":[109],"propose":[111],"train":[113],"network":[115],"by":[116],"directly":[117],"optimizing":[118],"level":[120],"SDR":[121],"a":[123],"permutation":[124],"invariant":[125],"(PIT)":[127],"style.":[128],"We":[129],"execute":[130],"generative":[131],"adversarial":[132],"(GAT)":[134],"throughout":[135],"training,":[137],"makes":[139],"indistinguishable":[143],"from":[144],"real":[146],"one.":[147],"Our":[148],"experiments":[149],"on":[150,173],"public":[153],"WSJ0-2mix":[154],"data":[155],"corpus":[156],"demonstrate":[157],"new":[160],"scheme":[161],"can":[162],"produce":[163],"more":[164],"discriminative":[165],"leading":[169],"performance":[171],"improvement":[172],"speaker":[175],"separation":[176],"task.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}