{"id":"https://openalex.org/W4391021752","doi":"https://doi.org/10.1109/asru57964.2023.10389733","title":"Toward Universal Speech Enhancement For Diverse Input Conditions","display_name":"Toward Universal Speech Enhancement For Diverse Input Conditions","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021752","doi":"https://doi.org/10.1109/asru57964.2023.10389733"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":["CN","US"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Carnegie Mellon University, USA","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013385059","display_name":"Kohei Saijo","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"]},{"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":["JP","US"],"is_corresponding":false,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Waseda University,Japan","Carnegie Mellon University, USA","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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/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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.995199978351593,"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":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891811728477478},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6755290627479553},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6516387462615967},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6217178702354431},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5612305402755737},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5577013492584229},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5522550940513611},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5378711819648743},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5229435563087463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5104309916496277},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4351615905761719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.406612753868103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3406546115875244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11454415321350098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891811728477478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6755290627479553},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6516387462615967},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6217178702354431},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5612305402755737},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5577013492584229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5522550940513611},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5378711819648743},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5229435563087463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5104309916496277},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4351615905761719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.406612753868103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3406546115875244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11454415321350098},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1989314204","https://openalex.org/W2044893557","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2514828952","https://openalex.org/W2559260703","https://openalex.org/W2609317876","https://openalex.org/W2892163332","https://openalex.org/W2930648092","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W3015191643","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3032514799","https://openalex.org/W3096893582","https://openalex.org/W3097906045","https://openalex.org/W3151851237","https://openalex.org/W3160191260","https://openalex.org/W3174770825","https://openalex.org/W3197912330","https://openalex.org/W3207360934","https://openalex.org/W3209490467","https://openalex.org/W3211779545","https://openalex.org/W3213188934","https://openalex.org/W4210849719","https://openalex.org/W4221144097","https://openalex.org/W4221153233","https://openalex.org/W4224917453","https://openalex.org/W4224936432","https://openalex.org/W4225302959","https://openalex.org/W4225310539","https://openalex.org/W4226162428","https://openalex.org/W4281820413","https://openalex.org/W4283326514","https://openalex.org/W4286896457","https://openalex.org/W4297841603","https://openalex.org/W4311000453","https://openalex.org/W4312857524","https://openalex.org/W4372260127","https://openalex.org/W4372260557","https://openalex.org/W4372271367","https://openalex.org/W4385822313","https://openalex.org/W6769228193","https://openalex.org/W6779944756","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2396048001","https://openalex.org/W2905188205","https://openalex.org/W1559044324"],"abstract_inverted_index":{"The":[0],"past":[1],"decade":[2],"has":[3],"witnessed":[4],"substantial":[5],"growth":[6],"of":[7,29,86,98,127],"data-driven":[8],"speech":[9],"enhancement":[10],"(SE)":[11],"techniques":[12],"thanks":[13],"to":[14,82],"deep":[15],"learning.":[16],"While":[17],"existing":[18,115],"approaches":[19],"have":[20],"shown":[21],"impressive":[22],"performance":[23],"in":[24],"some":[25],"common":[26],"datasets,":[27],"most":[28],"them":[30],"are":[31],"designed":[32],"only":[33,47],"for":[34],"a":[35,42,49,71,91,109,124],"single":[36,50,72,92,133],"condition":[37],"(e.g.,":[38,52],"single-channel,":[39],"multi-channel,":[40],"or":[41,46,54],"fixed":[43],"sampling":[44,104],"frequency)":[45],"consider":[48],"task":[51],"denoising":[53],"dereverberation).":[55],"Currently,":[56],"there":[57],"is":[58,96],"no":[59],"universal":[60,110],"SE":[61,93,111],"approach":[62],"that":[63,95,130],"can":[64,135],"effectively":[65],"handle":[66,137],"diverse":[67,138],"input":[68],"conditions":[69,139],"with":[70,118,140],"model.":[73],"In":[74],"this":[75,84],"paper,":[76],"we":[77,89,107],"make":[78],"the":[79,131],"first":[80],"attempt":[81],"investigate":[83],"line":[85],"research.":[87],"First,":[88],"devise":[90],"model":[94,134],"independent":[97],"microphone":[99],"channels,":[100],"signal":[101],"lengths,":[102],"and":[103],"frequencies.":[105],"Second,":[106],"design":[108],"benchmark":[112],"by":[113],"combining":[114],"public":[116],"corpora":[117],"multiple":[119],"conditions.":[120],"Our":[121],"experiments":[122],"on":[123],"wide":[125],"range":[126],"datasets":[128],"show":[129],"proposed":[132],"successfully":[136],"strong":[141],"performance.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}