{"id":"https://openalex.org/W2900132857","doi":"https://doi.org/10.1109/iwaenc.2018.8521243","title":"Phase Reconstruction with Learned Time-Frequency Representations for Single-Channel Speech Separation","display_name":"Phase Reconstruction with Learned Time-Frequency Representations for Single-Channel Speech Separation","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900132857","doi":"https://doi.org/10.1109/iwaenc.2018.8521243","mag":"2900132857"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"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":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), 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), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7185570001602173},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6898819208145142},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6279685497283936},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6200971603393555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5954406261444092},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5438658595085144},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5307536125183105},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.529701292514801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5227239727973938},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5073918700218201},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.44474610686302185},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43433383107185364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43104174733161926},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42130231857299805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37169304490089417},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.30475571751594543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18654313683509827},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15178221464157104},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.08425194025039673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185570001602173},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6898819208145142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6279685497283936},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6200971603393555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5954406261444092},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5438658595085144},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5307536125183105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.529701292514801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227239727973938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5073918700218201},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.44474610686302185},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43433383107185364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43104174733161926},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42130231857299805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37169304490089417},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.30475571751594543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18654313683509827},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15178221464157104},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.08425194025039673},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1831449718","https://openalex.org/W2095072097","https://openalex.org/W2120847449","https://openalex.org/W2156379660","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2401387233","https://openalex.org/W2552071709","https://openalex.org/W2635471793","https://openalex.org/W2734774145","https://openalex.org/W2795505790","https://openalex.org/W2891405874","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963103134","https://openalex.org/W2963443859","https://openalex.org/W2963751183","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964328256","https://openalex.org/W4297801963","https://openalex.org/W6631190155","https://openalex.org/W6638670064","https://openalex.org/W6737894438","https://openalex.org/W6743462201","https://openalex.org/W6749821626","https://openalex.org/W6750558598","https://openalex.org/W6750842128","https://openalex.org/W6752109149"],"related_works":["https://openalex.org/W2773120646","https://openalex.org/W2604802223","https://openalex.org/W2920938200","https://openalex.org/W2984883371","https://openalex.org/W11765363","https://openalex.org/W126779703","https://openalex.org/W2766146978","https://openalex.org/W3108696707","https://openalex.org/W2641889749","https://openalex.org/W2901504266"],"abstract_inverted_index":{"Progress":[0],"in":[1,87],"solving":[2],"the":[3,9,19,125,129,139],"cocktail":[4],"party":[5],"problem,":[6],"i.e.,":[7],"separating":[8],"speech":[10],"from":[11,110],"multiple":[12],"overlapping":[13],"speakers,":[14],"has":[15],"recently":[16],"accelerated":[17],"with":[18],"invention":[20],"of":[21,44,92,107,116,124],"techniques":[22],"such":[23],"as":[24,84],"deep":[25,68],"clustering":[26],"and":[27,41,80,134],"permutation":[28],"free":[29],"mask":[30],"inference.":[31],"These":[32],"approaches":[33],"typically":[34],"focus":[35],"on":[36,64,128],"estimating":[37],"target":[38],"STFT":[39],"magnitudes":[40],"ignore":[42],"problems":[43],"phase":[45,53,77,119],"inconsistency.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,98],"explicitly":[51],"integrate":[52],"reconstruction":[54,78,120],"into":[55],"our":[56,88,100],"separation":[57],"algorithm":[58,79],"using":[59,93],"a":[60,76,85,104],"loss":[61],"function":[62],"defined":[63,73],"time-domain":[65],"signals.":[66],"A":[67],"neural":[69],"network":[70,101],"structure":[71],"is":[72],"by":[74],"unfolding":[75],"treating":[81],"each":[82],"iteration":[83],"layer":[86],"network.":[89],"Furthermore,":[90],"instead":[91],"fixed":[94],"STFT/iSTFT":[95],"time-frequency":[96],"representations,":[97],"allow":[99],"to":[102,144],"learn":[103],"modified":[105],"version":[106],"these":[108,117],"representations":[109,141],"data.":[111],"We":[112],"compare":[113],"several":[114],"variants":[115],"unfolded":[118],"networks":[121],"achieving":[122],"state":[123],"art":[126],"results":[127],"publicly":[130],"available":[131],"wsj0-2mix":[132],"dataset,":[133],"show":[135],"improved":[136],"performance":[137],"when":[138],"STFT/iSTFT-like":[140],"are":[142],"allowed":[143],"adapt.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}