{"id":"https://openalex.org/W4372349226","doi":"https://doi.org/10.1109/icassp49357.2023.10097247","title":"A Framework for Unified Real-Time Personalized and Non-Personalized Speech Enhancement","display_name":"A Framework for Unified Real-Time Personalized and Non-Personalized Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349226","doi":"https://doi.org/10.1109/icassp49357.2023.10097247"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097247","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritwik Giri","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066642036","display_name":"Devansh Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devansh Shah","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082904207","display_name":"Michael M. Goodwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Goodwin","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Amazon Web Services","University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61551319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T13289","display_name":"Infant Health and Development","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132573962211609},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7554030418395996},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6995046138763428},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.632902979850769},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6271436214447021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5097765326499939},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4967718720436096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44147995114326477},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42348435521125793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41695499420166016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132573962211609},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7554030418395996},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6995046138763428},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.632902979850769},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6271436214447021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5097765326499939},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4967718720436096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44147995114326477},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42348435521125793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41695499420166016},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097247","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2949756029","https://openalex.org/W2951130829","https://openalex.org/W2969985801","https://openalex.org/W2973062255","https://openalex.org/W2991951409","https://openalex.org/W3010925296","https://openalex.org/W3015306128","https://openalex.org/W3015623828","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3095248373","https://openalex.org/W3096090308","https://openalex.org/W3096105647","https://openalex.org/W3097034112","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3160085755","https://openalex.org/W3162534564","https://openalex.org/W3198543387","https://openalex.org/W4221149546","https://openalex.org/W4224917453","https://openalex.org/W4224919629","https://openalex.org/W4224925682","https://openalex.org/W4225302959","https://openalex.org/W4225905067","https://openalex.org/W4283320926","https://openalex.org/W4292969786","https://openalex.org/W6757632829","https://openalex.org/W6771538394","https://openalex.org/W6839547487"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W1565692302"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,50,76],"present":[4],"an":[5],"approach":[6],"to":[7,66,99,126],"train":[8],"a":[9,28,72,121],"single":[10],"speech":[11,21,61,92],"enhancement":[12,37,93],"network":[13],"that":[14,32,79,101,116],"can":[15],"perform":[16],"both":[17,88],"personalized":[18,89],"and":[19,47,63,90,95],"non-personalized":[20,91],"enhancement.":[22],"This":[23],"is":[24,120],"achieved":[25],"by":[26,55],"incorporating":[27],"frame-wise":[29],"conditioning":[30],"input":[31],"specifies":[33],"the":[34,41,44,56,80,112,117],"type":[35],"of":[36,43,60,111],"output.":[38],"To":[39],"improve":[40],"quality":[42],"enhanced":[45],"output":[46],"mitigate":[48],"oversuppression,":[49],"experiment":[51],"with":[52],"re-weighting":[53],"frames":[54],"presence":[57],"or":[58],"absence":[59],"activity":[62],"applying":[64],"augmentations":[65],"speaker":[67],"embeddings.":[68],"By":[69],"training":[70],"under":[71],"multi-task":[73],"learning":[74],"setting,":[75],"empirically":[77],"show":[78],"proposed":[81,113],"unified":[82,118],"model":[83,119],"obtains":[84],"promising":[85],"results":[86],"on":[87],"benchmarks":[94],"reaches":[96],"similar":[97],"performance":[98,110],"models":[100,130],"are":[102],"trained":[103],"specialized":[104],"for":[105],"either":[106],"task.":[107],"The":[108],"strong":[109],"method":[114],"demonstrates":[115],"more":[122],"economical":[123],"alternative":[124],"compared":[125],"keeping":[127],"separate":[128],"task-specific":[129],"during":[131],"inference.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}