{"id":"https://openalex.org/W2962905190","doi":"https://doi.org/10.21437/interspeech.2018-1629","title":"End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction","display_name":"End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962905190","doi":"https://doi.org/10.21437/interspeech.2018-1629","mag":"2962905190"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1629","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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"]},{"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":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA","Mitsubishi Electric Research Laboratories (MERL), USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","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), USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","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, USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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 Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I4210159266","https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":15.0892,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.99369229,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2708","last_page":"2712"},"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":0.9988999962806702,"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":0.9988999962806702,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7553724050521851},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6804482936859131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.639301598072052},{"id":"https://openalex.org/keywords/signal-reconstruction","display_name":"Signal reconstruction","score":0.5531826019287109},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5262830853462219},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5097236037254333},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.46513456106185913},{"id":"https://openalex.org/keywords/phase-distortion","display_name":"Phase distortion","score":0.44288167357444763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4348652958869934},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.4339592158794403},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4267440438270569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40798765420913696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2762010395526886},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.2337813675403595},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18516457080841064},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.15997526049613953},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14244216680526733},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10941192507743835}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7553724050521851},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6804482936859131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639301598072052},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.5531826019287109},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5262830853462219},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5097236037254333},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.46513456106185913},{"id":"https://openalex.org/C57747864","wikidata":"https://www.wikidata.org/wiki/Q7180948","display_name":"Phase distortion","level":3,"score":0.44288167357444763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4348652958869934},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.4339592158794403},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4267440438270569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40798765420913696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2762010395526886},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2337813675403595},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18516457080841064},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.15997526049613953},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14244216680526733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10941192507743835},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1629","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1723619723","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2013419672","https://openalex.org/W2023082191","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2079362249","https://openalex.org/W2095072097","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2129116669","https://openalex.org/W2156379660","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2401387233","https://openalex.org/W2460742184","https://openalex.org/W2513732569","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2609317876","https://openalex.org/W2635471793","https://openalex.org/W2698117193","https://openalex.org/W2711335087","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2747161606","https://openalex.org/W2891405874","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2963443859","https://openalex.org/W2963828919","https://openalex.org/W2964058413"],"related_works":["https://openalex.org/W2008311543","https://openalex.org/W2802845977","https://openalex.org/W2078793534","https://openalex.org/W2318109418","https://openalex.org/W2120847449","https://openalex.org/W3097412542","https://openalex.org/W1907622544","https://openalex.org/W2904255108","https://openalex.org/W2070508296","https://openalex.org/W2161223648"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"end-to-end":[4],"approach":[5,159],"for":[6,74,109,115,140,175],"single-channel":[7],"speaker-independent":[8],"multi-speaker":[9],"speech":[10],"separation,":[11],"where":[12],"time-frequency":[13],"(T-F)":[14],"masking,":[15,147],"the":[16,39,48,61,68,112,123,141,145,154,188],"short-time":[17],"Fourier":[18],"transform":[19],"(STFT),":[20],"and":[21,94,107,168,181],"its":[22],"inverse":[23,95],"are":[24,72,100,126],"represented":[25,88],"as":[26,89],"layers":[27],"within":[28],"a":[29,36,43,84,90,183],"deep":[30,176],"network.Previous":[31],"approaches,":[32],"rather":[33],"than":[34],"computing":[35],"loss":[37,45,62],"on":[38,47,67],"reconstructed":[40,69],"signal,":[41],"used":[42,129],"surrogate":[44],"based":[46,178],"target":[49],"STFT":[50,93,96],"magnitudes.This":[51],"ignores":[52],"reconstruction":[53,86,180],"error":[54],"introduced":[55],"by":[56],"phase":[57,85,114,132,179],"inconsistency.In":[58],"our":[59,158],"approach,":[60],"function":[63],"is":[64,119],"directly":[65],"defined":[66],"signals,":[70],"which":[71],"optimized":[73],"best":[75],"separation.In":[76],"addition,":[77],"we":[78],"train":[79],"through":[80],"unfolded":[81],"iterations":[82],"of":[83,92,144],"algorithm,":[87],"series":[91],"layers.While":[97],"mask":[98,150],"values":[99,151],"typically":[101],"limited":[102],"to":[103,127,148],"lie":[104],"between":[105],"zero":[106],"one":[108],"approaches":[110],"using":[111],"mixture":[113],"reconstruction,":[116],"this":[117],"limitation":[118],"less":[120],"relevant":[121],"if":[122],"estimated":[124],"magnitudes":[125],"be":[128],"together":[130],"with":[131],"reconstruction.We":[133],"thus":[134],"propose":[135],"several":[136],"novel":[137],"activation":[138],"functions":[139],"output":[142],"layer":[143],"T-F":[146],"allow":[149],"beyond":[152],"one.On":[153],"publiclyavailable":[155],"wsj0-2mix":[156],"dataset,":[157],"achieves":[160],"state-ofthe-art":[161],"12.6":[162],"dB":[163,170],"scale-invariant":[164],"signal-to-distortion":[165],"ratio":[166],"(SI-SDR)":[167],"13.1":[169],"SDR,":[171],"revealing":[172],"new":[173],"possibilities":[174],"learning":[177],"representing":[182],"fundamental":[184],"progress":[185],"towards":[186],"solving":[187],"notoriously-hard":[189],"cocktail":[190],"party":[191],"problem.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}