{"id":"https://openalex.org/W2889134433","doi":"https://doi.org/10.21437/interspeech.2018-1773","title":"PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation","display_name":"PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889134433","doi":"https://doi.org/10.21437/interspeech.2018-1773","mag":"2889134433"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1773","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1773","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/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050546237","display_name":"Purvi Agrawal","orcid":"https://orcid.org/0000-0002-1165-8348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Purvi Agrawal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050759941","display_name":"Nabarun Goswami","orcid":"https://orcid.org/0000-0002-3960-5627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nabarun Goswami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101589290"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9551,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98504065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998999834060669,"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":0.9990000128746033,"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":0.6810592412948608},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6706607341766357},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6317793130874634},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.535445511341095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.518474280834198},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4709744453430176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38450807332992554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2955542802810669},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1430164873600006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12062975764274597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09717583656311035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6810592412948608},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6706607341766357},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6317793130874634},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.535445511341095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.518474280834198},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4709744453430176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38450807332992554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955542802810669},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1430164873600006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12062975764274597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09717583656311035},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1773","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1773","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"},{"id":"pmh:oai:eprints.iisc.ac.in:62926","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1537919901","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W2023082191","https://openalex.org/W2046736932","https://openalex.org/W2078528584","https://openalex.org/W2095072097","https://openalex.org/W2120847449","https://openalex.org/W2138995394","https://openalex.org/W2156379660","https://openalex.org/W2164764235","https://openalex.org/W2168793898","https://openalex.org/W2291877678","https://openalex.org/W2401387233","https://openalex.org/W2511710182","https://openalex.org/W2594251744","https://openalex.org/W2774707525","https://openalex.org/W2775265115","https://openalex.org/W2881244050","https://openalex.org/W2953318193","https://openalex.org/W2963543871","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2964005873"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W1971388572","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Previous":[0],"research":[1],"on":[2,7,14],"audio":[3],"source":[4,143,165],"separation":[5,53,166],"based":[6,133],"deep":[8],"neural":[9],"networks":[10],"(DNNs)":[11],"mainly":[12],"focuses":[13],"estimating":[15],"the":[16,26,32,50,61,65,68,78,84,90,109,138,141,145,155],"magnitude":[17,34],"spectrum":[18],"of":[19,25,52,64,86,92,140],"target":[20,42,142],"sources":[21],"and":[22,121,163,169],"typically,":[23],"phase":[24,43,66,72,79,110,119,139],"mixture":[27],"signal":[28],"is":[29,44,73],"combined":[30],"with":[31,67,89],"estimated":[33],"spectra":[35],"in":[36,144,158],"an":[37],"ad-hoc":[38],"way.":[39],"Although":[40],"recovering":[41],"assumed":[45],"to":[46,59,76,99,107,125],"be":[47,57],"important":[48],"for":[49,97],"improvement":[51],"quality,":[54],"it":[55,82,95],"can":[56],"difficult":[58,96],"handle":[60],"periodic":[62],"nature":[63],"regression":[69],"approach.":[70],"Unwrapping":[71],"one":[74],"way":[75],"eliminate":[77],"discontinuity,":[80],"however,":[81],"increases":[83],"range":[85],"value":[87],"along":[88],"times":[91],"unwrapping,":[93],"making":[94],"DNNs":[98],"model.":[100],"To":[101],"overcome":[102],"this":[103],"difficulty,":[104],"we":[105],"propose":[106],"treat":[108],"estimation":[111],"problem":[112,116],"as":[113],"a":[114],"classification":[115,132],"by":[117],"discretizing":[118],"values":[120],"assigning":[122],"class":[123],"indices":[124],"them.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"our":[131],"approach":[134,157],"1)":[135],"successfully":[136],"recovers":[137],"discretized":[146],"domain,":[147],"2)":[148],"improves":[149],"signal-to":[150],"distortion":[151],"ratio":[152],"(SDR)":[153],"over":[154],"regression-based":[156],"both":[159],"speech":[160],"enhancement":[161],"task":[162],"music":[164],"(MSS)":[167],"task,":[168],"3)":[170],"outperforms":[171],"state-of-the-art":[172],"MSS.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}