{"id":"https://openalex.org/W2939397531","doi":"https://doi.org/10.1109/icassp.2019.8682587","title":"The Phasebook: Building Complex Masks via Discrete Representations for Source Separation","display_name":"The Phasebook: Building Complex Masks via Discrete Representations for Source Separation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939397531","doi":"https://doi.org/10.1109/icassp.2019.8682587","mag":"2939397531"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682587","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/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"]}]},{"author_position":"middle","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":"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), 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":"middle","author":{"id":"https://openalex.org/A5040998234","display_name":"Andy M. Sarroff","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":"Andy Sarroff","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/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research in Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research in Cambridge, MA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.7378117442131042},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.564230740070343},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5324016213417053},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4854717552661896},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47516104578971863},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44316524267196655},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.42432650923728943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39728492498397827},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3538641929626465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17734834551811218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378117442131042},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.564230740070343},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5324016213417053},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4854717552661896},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47516104578971863},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44316524267196655},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.42432650923728943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39728492498397827},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3538641929626465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17734834551811218},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682587","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1897240248","https://openalex.org/W2046869671","https://openalex.org/W2078528584","https://openalex.org/W2095072097","https://openalex.org/W2156379660","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2406138296","https://openalex.org/W2407624275","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2788518788","https://openalex.org/W2889134433","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2900132857","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W6713555565","https://openalex.org/W6713658392","https://openalex.org/W6743462201","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2062195135","https://openalex.org/W4321636575","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W1986418932","https://openalex.org/W1984019423","https://openalex.org/W2156919374","https://openalex.org/W35446969"],"abstract_inverted_index":{"Deep":[0],"learning":[1,146],"based":[2,95],"speech":[3],"enhancement":[4],"and":[5,107,129,135],"source":[6],"separation":[7],"systems":[8,27],"have":[9],"recently":[10],"reached":[11],"unprecedented":[12],"levels":[13],"of":[14,33,52,65,70,93,100,117,163,189],"quality,":[15],"to":[16,45,48,85,140,154],"the":[17,31,53,68,71,79,101,105,108,171,175,187],"point":[18],"that":[19,119],"performance":[20,159,188],"is":[21,62,73],"reaching":[22],"a":[23,34,42,49,63,90,97,114,122,178],"new":[24,91],"ceiling.":[25],"Most":[26],"rely":[28],"on":[29,96,158,174],"estimating":[30],"magnitude":[32],"target":[35],"source,":[36],"either":[37],"directly":[38,120],"or":[39],"by":[40],"computing":[41],"real-valued":[43],"mask":[44],"be":[46],"applied":[47],"time-frequency":[50],"representation":[51,99],"mixture":[54,72,106],"signal.":[55,82],"A":[56],"limiting":[57],"factor":[58],"in":[59,137,143],"such":[60],"approaches":[61,192],"lack":[64],"phase":[66,69,87,102,167,196],"estimation:":[67],"most":[74],"often":[75],"used":[76],"when":[77],"reconstructing":[78],"estimated":[80],"time-domain":[81],"We":[83,110,125,148,169],"propose":[84],"estimate":[86],"using":[88,165],"\"phasebook\",":[89],"type":[92,116],"layer":[94,118],"discrete":[98,166],"difference":[103],"between":[104],"target.":[109],"also":[111,149],"introduce":[112],"\"combook\",":[113],"similar":[115],"estimates":[121],"complex":[123],"mask.":[124],"present":[126,150],"various":[127,161],"training":[128],"inference":[130],"schemes":[131],"involving":[132],"these":[133],"representations,":[134],"explain":[136],"particular":[138],"how":[139],"include":[141],"them":[142],"an":[144,151],"end-to-end":[145],"framework.":[147],"oracle":[152],"study":[153],"assess":[155],"upper":[156],"bounds":[157],"for":[160,181],"types":[162],"masks":[164],"representations.":[168],"evaluate":[170],"proposed":[172],"methods":[173],"wsj0-2mix":[176],"dataset,":[177],"well-studied":[179],"corpus":[180],"single-channel":[182],"speaker-independent":[183],"speaker":[184],"separation,":[185],"matching":[186],"state-of-the-art":[190],"mask-based":[191],"without":[193],"requiring":[194],"additional":[195],"reconstruction":[197],"steps.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}