{"id":"https://openalex.org/W2803023894","doi":"https://doi.org/10.1109/icassp.2018.8462269","title":"Sound Source Separation Using Phase Difference and Reliable Mask Selection Selection","display_name":"Sound Source Separation Using Phase Difference and Reliable Mask Selection Selection","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2803023894","doi":"https://doi.org/10.1109/icassp.2018.8462269","mag":"2803023894"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100684423","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-2526-4371"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042577114","display_name":"Anjali Menon","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjali Menon","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"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":"Michiel Bacchiani","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Stern","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1639,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79091442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5559","last_page":"5563"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7790883779525757},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.706016480922699},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6438807845115662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6054061055183411},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5944746732711792},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5837911367416382},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5185188055038452},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5056633949279785},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5008285045623779},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4655974805355072},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4638599753379822},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.45297449827194214},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4275953471660614},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4248805642127991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2533281445503235},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1833992898464203},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14971181750297546}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7790883779525757},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.706016480922699},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6438807845115662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6054061055183411},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5944746732711792},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5837911367416382},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5185188055038452},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5056633949279785},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5008285045623779},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4655974805355072},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4638599753379822},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45297449827194214},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4275953471660614},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4248805642127991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2533281445503235},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1833992898464203},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14971181750297546},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":32,"referenced_works":["https://openalex.org/W118588063","https://openalex.org/W167318317","https://openalex.org/W169229064","https://openalex.org/W587794757","https://openalex.org/W1566425957","https://openalex.org/W1586342741","https://openalex.org/W1600744878","https://openalex.org/W1983108229","https://openalex.org/W2034040413","https://openalex.org/W2041733487","https://openalex.org/W2062164080","https://openalex.org/W2063656732","https://openalex.org/W2103681028","https://openalex.org/W2130775302","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2326699523","https://openalex.org/W2396889049","https://openalex.org/W2400339399","https://openalex.org/W2400570867","https://openalex.org/W2407277936","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2702006285","https://openalex.org/W2766930522","https://openalex.org/W2963920996","https://openalex.org/W2964138484","https://openalex.org/W4232282348","https://openalex.org/W6617368339","https://openalex.org/W6688428952"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W1656519308","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2042717753","https://openalex.org/W164103134","https://openalex.org/W2022849831","https://openalex.org/W2077498359"],"abstract_inverted_index":{"In":[0],"this":[1,62],"paper,":[2],"we":[3],"present":[4],"an":[5],"algorithm":[6,40,63],"called":[7],"Reliable":[8],"Mask":[9],"Selection-Phase":[10],"Difference":[11],"Channel":[12],"Weighting":[13],"(RMS-PDCW)":[14],"which":[15,74],"selects":[16,41],"the":[17,26,34,46,49,54,70,82],"target":[18],"source":[19,24,52],"masked":[20],"by":[21],"a":[22],"noise":[23,91],"using":[25,33,45,77],"Angle":[27],"of":[28,57,87],"Arrival":[29],"(AoA)":[30],"information":[31,47],"calculated":[32],"phase":[35],"difference":[36],"information.":[37],"The":[38],"RMS-PDCW":[39],"masks":[42],"to":[43,109],"apply":[44],"about":[48],"localized":[50],"sound":[51],"and":[53,89,99,102],"onset":[55],"detection":[56],"speech.":[58],"We":[59],"demonstrate":[60],"that":[61],"shows":[64],"relatively":[65],"5.3":[66],"percent":[67],"improvement":[68],"over":[69],"baseline":[71],"acoustic":[72],"model,":[73],"was":[75],"multistyle-trained":[76],"22":[78],"million":[79],"utterances":[80],"on":[81],"simulated":[83],"test":[84],"set":[85],"consisting":[86],"real-world":[88],"interfering-speaker":[90],"with":[92],"reverberation":[93],"time":[94],"distribution":[95,104],"between":[96,105],"0":[97,106],"ms":[98,101],"900":[100],"SNR":[103],"dB":[107],"up":[108],"clean.":[110]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
