{"id":"https://openalex.org/W4392909610","doi":"https://doi.org/10.1109/icassp48485.2024.10448155","title":"Improving Design of Input Condition Invariant Speech Enhancement","display_name":"Improving Design of Input Condition Invariant Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909610","doi":"https://doi.org/10.1109/icassp48485.2024.10448155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448155","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":"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/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"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":"Jee-weon Jung","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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10696","last_page":"10700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"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":0.9768000245094299,"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/speech-enhancement","display_name":"Speech enhancement","score":0.584932804107666},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5539056658744812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5466492772102356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47054415941238403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2817739248275757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2311723828315735},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08072802424430847}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.584932804107666},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5539056658744812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5466492772102356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47054415941238403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2817739248275757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2311723828315735},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08072802424430847},{"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/icassp48485.2024.10448155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448155","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":[],"awards":[{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2514828952","https://openalex.org/W2559260703","https://openalex.org/W2609317876","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2996820600","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3032514799","https://openalex.org/W3096893582","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3138516171","https://openalex.org/W3151851237","https://openalex.org/W3201773091","https://openalex.org/W3205004157","https://openalex.org/W3207918547","https://openalex.org/W4221161255","https://openalex.org/W4224936432","https://openalex.org/W4225302959","https://openalex.org/W4253928870","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W4385822313","https://openalex.org/W4391021752","https://openalex.org/W6647660671","https://openalex.org/W6810244463","https://openalex.org/W6810619885"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"Building":[0],"a":[1,14,29,57,115,138],"single":[2,30],"universal":[3],"speech":[4],"enhancement":[5],"(SE)":[6],"system":[7],"that":[8,32,90,112,120],"can":[9,128],"handle":[10],"arbitrary":[11],"input":[12,84],"is":[13,26,101],"demanded":[15],"but":[16],"underexplored":[17],"research":[18],"topic.":[19],"Towards":[20],"this":[21,75,105,133],"ultimate":[22],"goal,":[23],"one":[24],"direction":[25],"to":[27,81,125,142,164],"build":[28],"model":[31,58,88,193],"handles":[33],"diverse":[34],"audio":[35],"duration,":[36],"sampling":[37],"frequencies,":[38],"and":[39,44,131,160],"microphone":[40],"variations":[41],"in":[42,71,92],"noisy":[43],"reverberant":[45],"scenarios,":[46],"which":[47],"we":[48,77,107,118,147],"define":[49],"here":[50],"as":[51],"\"input":[52],"condition":[53,85,99],"invariant":[54,86],"SE\".":[55],"Such":[56],"was":[59],"recently":[60],"proposed":[61,181],"showing":[62],"promising":[63],"performance;":[64],"however,":[65],"its":[66],"multi-channel":[67],"performance":[68,91,156,186],"degraded":[69],"severely":[70],"real":[72,98,188],"conditions.":[73,189],"In":[74],"paper":[76],"propose":[78,148],"novel":[79,150],"architectures":[80],"improve":[82],"the":[83,109,121,165,177,180],"SE":[87],"so":[89],"simulated":[93],"conditions":[94],"remains":[95],"competitive":[96],"while":[97],"degradation":[100],"much":[102],"mitigated.":[103],"For":[104],"purpose,":[106],"redesign":[108,132],"key":[110],"components":[111],"comprise":[113],"such":[114],"system.":[116],"First,":[117],"identify":[119],"channel-modeling":[122],"module\u2019s":[123],"generalization":[124],"unseen":[126],"scenarios":[127],"be":[129,196],"suboptimal":[130],"module.":[134],"We":[135],"further":[136],"introduce":[137],"two-stage":[139],"training":[140,144],"strategy":[141],"enhance":[143],"efficiency.":[145],"Second,":[146],"two":[149],"dual-path":[151],"time-frequency":[152],"blocks,":[153],"demonstrating":[154],"superior":[155],"with":[157,183,191],"fewer":[158],"parameters":[159],"computational":[161],"costs":[162],"compared":[163],"existing":[166],"method.":[167],"All":[168],"proposals":[169],"combined,":[170],"experiments":[171],"on":[172,187],"various":[173],"public":[174],"datasets":[175],"validate":[176],"efficacy":[178],"of":[179],"model,":[182],"significantly":[184],"improved":[185],"Recipes":[190],"full":[192],"details":[194],"will":[195],"released":[197],"for":[198],"reproducibility":[199],"<sup":[200],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[201],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[202],".":[203]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}