{"id":"https://openalex.org/W1482149378","doi":"https://doi.org/10.1109/icassp.2015.7178061","title":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","display_name":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1482149378","doi":"https://doi.org/10.1109/icassp.2015.7178061","mag":"1482149378"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["TR","US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA","Sabanci University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Sabanci University, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Broadway, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":702,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"708","last_page":"712"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.7097240090370178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5280046463012695},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5204322934150696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5047889947891235},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5040615797042847},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5029551386833191},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4855170249938965},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.47919023036956787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4560522735118866},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44615086913108826},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44507065415382385},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.43967851996421814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38899967074394226},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20372191071510315},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10303911566734314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097240090370178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5280046463012695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5204322934150696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047889947891235},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5040615797042847},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5029551386833191},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4855170249938965},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.47919023036956787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4560522735118866},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44615086913108826},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44507065415382385},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.43967851996421814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38899967074394226},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20372191071510315},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10303911566734314},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.sabanciuniv.edu:28858","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.724.4733","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.4733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.sabanciuniv.edu/haerdogan/pubs/erdogan15icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"},{"id":"https://openalex.org/F4320337954","display_name":"Fondo para la Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/03stxzb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W1974774036","https://openalex.org/W1976951404","https://openalex.org/W1980741455","https://openalex.org/W1983133367","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2053165762","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2079362249","https://openalex.org/W2090681206","https://openalex.org/W2094461119","https://openalex.org/W2101045344","https://openalex.org/W2115055618","https://openalex.org/W2135029798","https://openalex.org/W2141411743","https://openalex.org/W2147455188","https://openalex.org/W2149648698","https://openalex.org/W3143596294","https://openalex.org/W6668037159","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W1969211203","https://openalex.org/W1517958729","https://openalex.org/W2092272653","https://openalex.org/W1630865680","https://openalex.org/W1992704972","https://openalex.org/W271627879","https://openalex.org/W4214692512","https://openalex.org/W2349444258","https://openalex.org/W2118992737"],"abstract_inverted_index":{"Separation":[0],"of":[1,54,71,86,102,113,130,148],"speech":[2,124],"embedded":[3],"in":[4,93,100,127],"non-stationary":[5],"interference":[6],"is":[7,37],"a":[8,27,38,47,76,153],"challenging":[9],"problem":[10],"that":[11,25,41,92],"has":[12,23,60],"recently":[13],"seen":[14],"dramatic":[15],"improvements":[16,109],"using":[17,46,115],"deep":[18,57],"network-based":[19],"methods.":[20],"Previous":[21],"work":[22],"shown":[24,63],"estimating":[26],"masking":[28],"function":[29,79],"to":[30,33,64,110,145],"be":[31,43],"applied":[32],"the":[34,82,87,111,128,135],"noisy":[35],"spectrum":[36],"viable":[39],"approach":[40],"can":[42],"improved":[44],"by":[45,122],"signal-approximation":[48],"based":[49,80],"objective":[50,78],"function.":[51],"Better":[52],"modeling":[53,112],"dynamics":[55],"through":[56],"recurrent":[58,117],"networks":[59],"also":[61,107],"been":[62],"improve":[65],"performance.":[66],"Here":[67],"we":[68],"pursue":[69],"both":[70],"these":[72],"directions.":[73],"We":[74,106],"develop":[75],"phase-sensitive":[77],"on":[81],"signal-to-noise":[83],"ratio":[84,104],"(SNR)":[85],"reconstructed":[88],"signal,":[89],"and":[90],"show":[91],"experiments":[94],"it":[95],"yields":[96],"uniformly":[97],"better":[98],"results":[99],"terms":[101],"signal-to-distortion":[103],"(SDR).":[105],"investigate":[108],"dynamics,":[114],"bidirectional":[116],"networks,":[118],"as":[119,121,152],"well":[120],"incorporating":[123],"recognition":[125,149],"outputs":[126],"form":[129],"alignment":[131],"vectors":[132],"concatenated":[133],"with":[134,150],"spectral":[136],"input":[137],"features.":[138],"Both":[139],"methods":[140],"yield":[141],"further":[142],"improvements,":[143],"pointing":[144],"tighter":[146],"integration":[147],"separation":[151],"promising":[154],"future":[155],"direction.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":109},{"year":2020,"cited_by_count":147},{"year":2019,"cited_by_count":99},{"year":2018,"cited_by_count":80},{"year":2017,"cited_by_count":44},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}