{"id":"https://openalex.org/W4392909903","doi":"https://doi.org/10.1109/icassp48485.2024.10447017","title":"uSee: Unified Speech Enhancement And Editing with Conditional Diffusion Models","display_name":"uSee: Unified Speech Enhancement And Editing with Conditional Diffusion Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909903","doi":"https://doi.org/10.1109/icassp48485.2024.10447017"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447017","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/A5012381843","display_name":"Muqiao Yang","orcid":"https://orcid.org/0000-0001-6273-0138"},"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":"Muqiao Yang","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/A5100458065","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-6253-2446"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100573226","display_name":"Yong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069215134","display_name":"Zhongweiyang Xu","orcid":null},"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":"Zhongweiyang Xu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","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":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.14,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8754571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7125","last_page":"7129"},"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":0.9988999962806702,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8445797562599182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7130299806594849},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6952455043792725},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6495938301086426},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46592020988464355},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4492994248867035},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4436340928077698},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43665817379951477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34654518961906433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445797562599182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7130299806594849},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6952455043792725},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6495938301086426},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46592020988464355},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4492994248867035},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4436340928077698},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43665817379951477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34654518961906433},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/icassp48485.2024.10447017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447017","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1991111872","https://openalex.org/W2044893557","https://openalex.org/W2141411743","https://openalex.org/W2405774341","https://openalex.org/W2593116425","https://openalex.org/W2696967604","https://openalex.org/W2952218014","https://openalex.org/W2959300817","https://openalex.org/W2963341071","https://openalex.org/W2972359262","https://openalex.org/W3036167779","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3161158930","https://openalex.org/W3161354387","https://openalex.org/W3161480375","https://openalex.org/W3209059054","https://openalex.org/W4200177005","https://openalex.org/W4211127940","https://openalex.org/W4221144097","https://openalex.org/W4225596771","https://openalex.org/W4245919820","https://openalex.org/W4288089799","https://openalex.org/W4297841480","https://openalex.org/W4300980117","https://openalex.org/W4362598673","https://openalex.org/W4380434618","https://openalex.org/W4396877837","https://openalex.org/W4400111385","https://openalex.org/W6765775151","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6845479124","https://openalex.org/W6851290578"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121"],"abstract_inverted_index":{"Speech":[0,39],"enhancement":[1,90,126],"aims":[2],"to":[3,20,28,49,76,94,121],"improve":[4],"the":[5,21,25,54,77,87,99,149],"quality":[6,13],"of":[7,12,23,66,86,148],"speech":[8,17,26,89,116,125,131,151],"signals":[9],"in":[10,57,114],"terms":[11],"and":[14,16,41,72,91,118,128,142],"intelligibility,":[15],"editing":[18,24,92,132],"refers":[19],"process":[22],"according":[27],"specific":[29],"user":[30],"needs.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,81],"propose":[36],"a":[37,58],"Unified":[38],"Enhancement":[40],"Editing":[42],"(uSee)":[43],"model":[44,93,109],"with":[45],"conditional":[46],"diffusion":[47,79],"models":[48],"handle":[50],"various":[51],"tasks":[52],"at":[53,154],"same":[55],"time":[56],"generative":[59,124],"manner.":[60],"Specifically,":[61],"by":[62],"providing":[63],"multiple":[64],"types":[65],"conditions":[67],"including":[68],"self-supervised":[69],"learning":[70],"embeddings":[71],"proper":[73],"text":[74,137],"prompts":[75],"score-based":[78],"model,":[80],"can":[82,110,129],"enable":[83],"controllable":[84],"generation":[85],"unified":[88],"perform":[95,130],"corresponding":[96],"actions":[97],"on":[98],"source":[100],"speech.":[101],"Our":[102],"experiments":[103],"show":[104],"that":[105],"our":[106],"proposed":[107],"uSee":[108],"achieve":[111],"superior":[112],"performance":[113],"both":[115],"denoising":[117],"dereverberation":[119],"compared":[120],"other":[122],"related":[123],"models,":[127],"given":[133],"desired":[134],"environmental":[135],"sound":[136],"description,":[138],"signal-to-noise":[139],"ratios":[140],"(SNR),":[141],"room":[143],"impulse":[144],"responses":[145],"(RIR).":[146],"Demos":[147],"generated":[150],"are":[152],"available":[153],"https://muqiaoy.github.io/usee.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}