{"id":"https://openalex.org/W3016026630","doi":"https://doi.org/10.1109/icassp40776.2020.9054265","title":"Mask-Dependent Phase Estimation for Monaural Speaker Separation","display_name":"Mask-Dependent Phase Estimation for Monaural Speaker Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016026630","doi":"https://doi.org/10.1109/icassp40776.2020.9054265","mag":"3016026630"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["CUNY,The Graduate Center,New York,NY,USA","The Graduate Center, CUNY, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"CUNY,The Graduate Center,New York,NY,USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"The Graduate Center, CUNY, New York, NY, USA","institution_ids":["https://openalex.org/I121847817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I83041322","display_name":"Brooklyn College","ror":"https://ror.org/019k4jq75","country_code":"US","type":"education","lineage":["https://openalex.org/I83041322"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I Mandel","raw_affiliation_strings":["CUNY,Brooklyn College,Brooklyn,NY,USA","Brooklyn College, CUNY, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"CUNY,Brooklyn College,Brooklyn,NY,USA","institution_ids":["https://openalex.org/I83041322"]},{"raw_affiliation_string":"Brooklyn College, CUNY, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I83041322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031088292"],"corresponding_institution_ids":["https://openalex.org/I121847817"],"apc_list":null,"apc_paid":null,"fwci":0.9092,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7319289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7269","last_page":"7273"},"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":0.9994999766349792,"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":0.9991999864578247,"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":0.7063900232315063},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6155059337615967},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5826756358146667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5537020564079285},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5481957197189331},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5153438448905945},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5098382830619812},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.47479692101478577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46358394622802734},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4514715075492859},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4102044999599457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3370976150035858},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32244640588760376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21053412556648254},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15241315960884094},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.14644569158554077},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14471358060836792},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08339473605155945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063900232315063},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6155059337615967},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5826756358146667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5537020564079285},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5481957197189331},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5153438448905945},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5098382830619812},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.47479692101478577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46358394622802734},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4514715075492859},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4102044999599457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3370976150035858},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32244640588760376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21053412556648254},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15241315960884094},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.14644569158554077},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14471358060836792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08339473605155945},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2156379660","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2296073425","https://openalex.org/W2407685581","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2711335087","https://openalex.org/W2891405874","https://openalex.org/W2894785362","https://openalex.org/W2899771611","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2963317762","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2972460025","https://openalex.org/W3123318516","https://openalex.org/W6714030504","https://openalex.org/W6750169759","https://openalex.org/W6756040250","https://openalex.org/W6948209416"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W4225639054","https://openalex.org/W1967434260","https://openalex.org/W2402466562","https://openalex.org/W2574021307"],"abstract_inverted_index":{"Speaker":[0],"separation":[1],"refers":[2],"to":[3,19,26,103,129,144,160],"isolating":[4],"speech":[5,70],"of":[6,40,47,67],"interest":[7],"in":[8,137,173],"a":[9,56,73,78,96,174],"multi-talker":[10],"environment.":[11],"Most":[12],"methods":[13],"apply":[14],"real-valued":[15],"Time-Frequency":[16],"(T-F)":[17],"masks":[18],"the":[20,28,38,41,44,48,65,68,83,88,92,105,110,113,131,134,139,148,153],"mixture":[21],"Short-Time":[22],"Fourier":[23],"Transform":[24],"(STFT)":[25],"reconstruct":[27],"clean":[29,49,69],"speech.":[30,50],"Hence":[31],"there":[32],"is":[33,141],"an":[34,120],"unavoidable":[35],"mismatch":[36],"between":[37],"phase":[39,46,60,66,106,127,140,154,165],"reconstruction":[42,166],"and":[43,91],"original":[45],"In":[51],"this":[52],"paper,":[53],"we":[54,94],"propose":[55,95,119],"simple":[57],"yet":[58],"effective":[59],"estimation":[61,155],"network":[62,156],"that":[63,152,162],"predicts":[64],"based":[71,108],"on":[72,109,133,147],"T-F":[74,89,114,135],"mask":[75,90,115],"predicted":[76],"by":[77],"chimera++":[79],"network.":[80],"To":[81],"overcome":[82],"label-permutation":[84],"problem":[85],"for":[86,126],"both":[87],"phase,":[93],"mask-dependent":[97],"permutation":[98],"invariant":[99],"training":[100],"(PIT)":[101],"criterion":[102],"select":[104],"signal":[107],"loss":[111,170],"from":[112],"prediction.":[116],"We":[117],"also":[118],"Inverse":[121],"Mask":[122],"Weighted":[123],"Loss":[124],"Function":[125],"prediction":[128],"focus":[130],"model":[132],"regions":[136],"which":[138],"more":[142,175],"difficult":[143],"predict.":[145],"Results":[146],"WSJ0-2mix":[149],"dataset":[150],"show":[151],"achieves":[157],"comparable":[158],"performance":[159],"models":[161],"use":[163],"iterative":[164],"or":[167],"end-to-end":[168],"time-domain":[169],"functions,":[171],"but":[172],"straightforward":[176],"manner.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}