{"id":"https://openalex.org/W4392902873","doi":"https://doi.org/10.1109/icassp48485.2024.10446743","title":"Unrestricted Global Phase Bias-Aware Single-Channel Speech Enhancement with Conformer-Based Metric Gan","display_name":"Unrestricted Global Phase Bias-Aware Single-Channel Speech Enhancement with Conformer-Based Metric Gan","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902873","doi":"https://doi.org/10.1109/icassp48485.2024.10446743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100362569","display_name":"Shiqi Zhang","orcid":"https://orcid.org/0000-0002-7155-9579"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shiqi Zhang","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110149808","display_name":"Zheng Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zheng Qiu","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["NTT Coporation,Japan","NTT Coporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Coporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Coporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Coporation,Japan","NTT Coporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Coporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Coporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100362569"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":2.2413,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8773893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1030"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7235260605812073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6717168688774109},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5330682396888733},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5150609016418457},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4732896685600281},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.46017447113990784},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.45732298493385315},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42775434255599976},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.42687052488327026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4234650135040283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37384817004203796},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3646211326122284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2300294041633606},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17253518104553223},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1323663294315338},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07987239956855774}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7235260605812073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717168688774109},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5330682396888733},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5150609016418457},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4732896685600281},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46017447113990784},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.45732298493385315},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42775434255599976},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.42687052488327026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4234650135040283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37384817004203796},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3646211326122284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2300294041633606},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17253518104553223},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1323663294315338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07987239956855774},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1509909212","https://openalex.org/W1552314771","https://openalex.org/W2057239882","https://openalex.org/W2067295501","https://openalex.org/W2120847449","https://openalex.org/W2144404214","https://openalex.org/W2403555780","https://openalex.org/W2603567530","https://openalex.org/W2802304149","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962911378","https://openalex.org/W2962935966","https://openalex.org/W2963341071","https://openalex.org/W2981022124","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3016109656","https://openalex.org/W3046669506","https://openalex.org/W3096709315","https://openalex.org/W3099330747","https://openalex.org/W3158243217","https://openalex.org/W3158779859","https://openalex.org/W3161748343","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3206809722","https://openalex.org/W3215881519","https://openalex.org/W4221143458","https://openalex.org/W4221158470","https://openalex.org/W4225309689","https://openalex.org/W4309210956","https://openalex.org/W4366548739","https://openalex.org/W4372260247","https://openalex.org/W4375869466","https://openalex.org/W4385807442","https://openalex.org/W4385823093","https://openalex.org/W6636438496","https://openalex.org/W6762114000","https://openalex.org/W6770232298"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2364594919","https://openalex.org/W2167092671","https://openalex.org/W1861706286","https://openalex.org/W2219338811","https://openalex.org/W2149583853","https://openalex.org/W2143002539","https://openalex.org/W4293472652","https://openalex.org/W4317932689","https://openalex.org/W2583155851"],"abstract_inverted_index":{"With":[0],"the":[1,10,17,24,35,55,61,86,92,111,119],"rapid":[2],"development":[3],"of":[4,12,20,80,90,114],"neural":[5,39,120],"networks":[6,14,40],"in":[7,23],"recent":[8],"years,":[9],"ability":[11],"various":[13],"to":[15,99],"enhance":[16],"magnitude":[18],"spectrum":[19,37,67],"noisy":[21],"speech":[22,26],"single-channel":[25],"enhancement":[27],"domain":[28],"has":[29],"become":[30],"exceptionally":[31],"outstanding.":[32],"However,":[33],"enhancing":[34],"phase":[36,66,71,81,94,116],"using":[38],"is":[41],"often":[42],"ineffective,":[43],"which":[44,109],"remains":[45],"a":[46,64,69,100,122,132],"challenging":[47],"problem.":[48],"In":[49],"this":[50,129],"paper,":[51],"we":[52,75],"found":[53],"that":[54,128],"human":[56],"ear":[57],"cannot":[58],"sensitively":[59],"perceive":[60],"difference":[62],"between":[63],"precise":[65,93,115],"and":[68,117],"biased":[70],"(BP)":[72],"spectrum.":[73,95],"Therefore,":[74],"propose":[76],"an":[77],"optimization":[78],"method":[79,130],"reconstruction,":[82],"allowing":[83],"freedom":[84],"on":[85],"global-phase":[87],"bias":[88],"instead":[89],"reconstructing":[91],"We":[96],"applied":[97],"it":[98],"Conformer-based":[101],"Metric":[102],"Generative":[103],"Adversarial":[104],"Networks":[105],"(CMGAN)":[106],"baseline":[107],"model,":[108],"relaxes":[110],"existing":[112],"constraints":[113],"gives":[118],"network":[121],"broader":[123],"learning":[124],"space.":[125],"Results":[126],"show":[127],"achieves":[131],"new":[133],"state-of-the-art":[134],"performance":[135],"without":[136],"incurring":[137],"additional":[138],"computational":[139],"overhead.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}