{"id":"https://openalex.org/W2894785362","doi":"https://doi.org/10.1109/jstsp.2019.2904183","title":"Phasebook and Friends: Leveraging Discrete Representations for Source Separation","display_name":"Phasebook and Friends: Leveraging Discrete Representations for Source Separation","publication_year":2019,"publication_date":"2019-03-11","ids":{"openalex":"https://openalex.org/W2894785362","doi":"https://doi.org/10.1109/jstsp.2019.2904183","mag":"2894785362"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2904183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2904183","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.01395","any_repository_has_fulltext":true},"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, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3451-171X","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, 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, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8597-6795","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, 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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040998234","display_name":"Andy M. Sarroff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Sarroff","raw_affiliation_strings":["iZotope, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iZotope, Cambridge, MA, USA","institution_ids":[]}]},{"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, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1249,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.99033574,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"13","issue":"2","first_page":"370","last_page":"382"},"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":0.9984999895095825,"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":0.7581584453582764},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6579136848449707},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4928305447101593},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4917057156562805},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43272367119789124},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42482858896255493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40535932779312134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36894863843917847},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3275832235813141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581584453582764},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6579136848449707},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4928305447101593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4917057156562805},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43272367119789124},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42482858896255493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40535932779312134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36894863843917847},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3275832235813141},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2019.2904183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2904183","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1810.01395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.01395","pdf_url":"https://arxiv.org/pdf/1810.01395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.01395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.01395","pdf_url":"https://arxiv.org/pdf/1810.01395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W160800111","https://openalex.org/W1482149378","https://openalex.org/W1897240248","https://openalex.org/W1963970749","https://openalex.org/W2046869671","https://openalex.org/W2095072097","https://openalex.org/W2101045344","https://openalex.org/W2119717200","https://openalex.org/W2121973264","https://openalex.org/W2138939691","https://openalex.org/W2156379660","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2401387233","https://openalex.org/W2406138296","https://openalex.org/W2407624275","https://openalex.org/W2460742184","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2734774145","https://openalex.org/W2788518788","https://openalex.org/W2797090057","https://openalex.org/W2889134433","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2899439440","https://openalex.org/W2900132857","https://openalex.org/W2900368655","https://openalex.org/W2952165242","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2963739817","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W3147539069","https://openalex.org/W4241811150","https://openalex.org/W6600441815","https://openalex.org/W6680324615","https://openalex.org/W6713555565","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W2980176872","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2912971006","https://openalex.org/W4323060069"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"and":[2,86,112,161,167],"source":[3,37],"separation":[4],"systems":[5,28],"based":[6,93],"on":[7,30,94,190,206],"deep":[8],"learning":[9,178],"have":[10],"recently":[11,114],"reached":[12],"unprecedented":[13],"levels":[14],"of":[15,34,50,63,68,91,133,195,221],"quality,":[16],"to":[17,43,46,101,129,148,172,186],"the":[18,32,51,66,69,77,134,149,203,207,219],"point":[19],"that":[20,97,152],"performance":[21,191,220],"is":[22,60,71],"reaching":[23],"a":[24,35,40,47,61,113,126,210],"new":[25,89],"ceiling.":[26],"Most":[27],"rely":[29],"estimating":[31,39],"magnitude":[33,121],"target":[36],"by":[38],"real-valued":[41],"mask":[42,136],"be":[44,99],"applied":[45],"time-frequency":[48,104],"representation":[49],"mixture":[52,70],"signal.":[53,80],"A":[54],"limiting":[55],"factor":[56],"in":[57,169,175],"such":[58],"approaches":[59,224],"lack":[62],"phase":[64,67,135,140,199,228],"estimation:":[65],"most":[72],"often":[73],"used":[74,100],"when":[75],"reconstructing":[76],"estimated":[78],"time-domain":[79],"Here,":[81],"we":[82],"propose":[83],"\u201cmagbook,\u201d":[84],"\u201cphasebook,\u201d":[85],"\u201ccombook,\u201d":[87],"three":[88],"types":[90,194],"layers":[92,107,124,144],"discrete":[95,198],"representations":[96],"can":[98],"estimate":[102,132,154],"complex":[103,155],"masks.":[105,156],"Magbook":[106],"extend":[108],"classical":[109],"sigmoidal":[110],"units":[111],"introduced":[115],"convex":[116],"softmax":[117],"activation":[118],"for":[119,192,213],"mask-based":[120,223],"estimation.":[122],"Phasebook":[123],"use":[125],"similar":[127],"structure":[128],"give":[130],"an":[131,146,176,183],"without":[137,225],"suffering":[138],"from":[139],"wrapping":[141],"issues.":[142],"Combook":[143],"are":[145],"alternative":[147],"magbook-phasebook":[150],"combination":[151],"directly":[153],"We":[157,180,201],"present":[158,182],"various":[159,193],"training":[160],"inference":[162],"schemes":[163],"involving":[164],"these":[165],"representations,":[166],"explain":[168],"particular":[170],"how":[171],"include":[173],"them":[174],"end-to-end":[177],"framework.":[179],"also":[181],"oracle":[184],"study":[185],"assess":[187],"upper":[188],"bounds":[189],"masks":[196],"using":[197],"representations.":[200],"evaluate":[202],"proposed":[204],"methods":[205],"wsj0-2mix":[208],"dataset,":[209],"well-studied":[211],"corpus":[212],"single-channel":[214],"speaker-independent":[215],"speaker":[216],"separation,":[217],"matching":[218],"state-of-the-art":[222],"requiring":[226],"additional":[227],"reconstruction":[229],"steps.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2018-10-12T00:00:00"}