{"id":"https://openalex.org/W4221144097","doi":"https://doi.org/10.1109/icassp43922.2022.9746901","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","display_name":"Conditional Diffusion Probabilistic Model for Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221144097","doi":"https://doi.org/10.1109/icassp43922.2022.9746901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746901","doi":"https://doi.org/10.1109/icassp43922.2022.9746901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5067198078","display_name":"Yen-Ju Lu","orcid":"https://orcid.org/0000-0001-8400-4188","observed_orcids":["https://orcid.org/0000-0001-8400-4188"]},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"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"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430","observed_orcids":["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,Language Technology Institute,Pittsburgh,PA,USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, 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","observed_orcids":["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,Language Technology Institute,Pittsburgh,PA,USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technology Institute,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112845052","display_name":"Alexander Richard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Richard","raw_affiliation_strings":["Reality Labs Research, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":"https://orcid.org/0009-0002-8732-0391","observed_orcids":["https://orcid.org/0009-0002-8732-0391"]},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418","observed_orcids":["https://orcid.org/0000-0001-6956-0418"]},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Research Center for Information Technology Innovation,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.2523,"has_fulltext":false,"cited_by_count":222,"citation_normalized_percentile":{"value":0.99715454,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7402","last_page":"7406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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":0.002199999988079071,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9810000061988831},{"id":"https://openalex.org/keywords/diffusion-probabilistic-models","display_name":"diffusion probabilistic models","score":0.9649999737739563},{"id":"https://openalex.org/keywords/conditional-diffusion","display_name":"conditional diffusion","score":0.7590000033378601},{"id":"https://openalex.org/keywords/reverse-process","display_name":"reverse process","score":0.6399999856948853},{"id":"https://openalex.org/keywords/non-gaussian-noise","display_name":"non-Gaussian noise","score":0.9419999718666077},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.7170000076293945},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.45399999618530273}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7492173314094543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470836639404297},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7176393866539001},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5506130456924438},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5082768797874451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.494170218706131},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47799864411354065},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.44795289635658264},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4394327700138092},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4260755479335785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4257497787475586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32213374972343445},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27466684579849243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15613767504692078},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1404951810836792},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746901","doi":"https://doi.org/10.1109/icassp43922.2022.9746901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1936725236","https://openalex.org/W1992475611","https://openalex.org/W2015069270","https://openalex.org/W2094721231","https://openalex.org/W2129069237","https://openalex.org/W2144404214","https://openalex.org/W2405774341","https://openalex.org/W2516547830","https://openalex.org/W2519091744","https://openalex.org/W2559260703","https://openalex.org/W2600556233","https://openalex.org/W2603567530","https://openalex.org/W2746457594","https://openalex.org/W2747161606","https://openalex.org/W2794950960","https://openalex.org/W2802304149","https://openalex.org/W2805233667","https://openalex.org/W2943895317","https://openalex.org/W2952218014","https://openalex.org/W2954275688","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2972436155","https://openalex.org/W2998832642","https://openalex.org/W3005621653","https://openalex.org/W3016056257","https://openalex.org/W3036167779","https://openalex.org/W3036367741","https://openalex.org/W3086154751","https://openalex.org/W3087665158","https://openalex.org/W3098403858","https://openalex.org/W3122887982","https://openalex.org/W3160324929","https://openalex.org/W3184410885","https://openalex.org/W4226320669","https://openalex.org/W4232282348"],"related_works":["https://openalex.org/W4416373993","https://openalex.org/W4392931780","https://openalex.org/W3184410885","https://openalex.org/W4408352278","https://openalex.org/W4380434618","https://openalex.org/W4403661504","https://openalex.org/W4392903364","https://openalex.org/W4393201353","https://openalex.org/W4403095773","https://openalex.org/W4405709885"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,53],"is":[2],"a":[3,50,74],"critical":[4],"component":[5],"of":[6,58,77,110,124],"many":[7],"user-oriented":[8],"audio":[9],"applications,":[10],"yet":[11],"current":[12],"systems":[13],"still":[14,33],"suffer":[15],"from":[16],"distorted":[17],"and":[18,48,67,119],"unnatural":[19],"outputs.":[20],"While":[21],"generative":[22,117],"models":[23,126],"have":[24],"shown":[25],"strong":[26,108],"potential":[27],"in":[28,36,44,88,98],"speech":[29,37,52,62,101],"synthesis,":[30],"they":[31],"are":[32],"lagging":[34],"behind":[35],"enhancement.":[38],"This":[39],"work":[40],"leverages":[41],"recent":[42],"advances":[43],"diffusion":[45,66,79,84],"probabilistic":[46,80,85],"models,":[47,118],"proposes":[49],"novel":[51],"algorithm":[54],"that":[55],"incorporates":[56],"characteristics":[57,132],"the":[59,65,78,99,111,121],"observed":[60],"noisy":[61],"signal":[63],"into":[64],"reverse":[68,90],"processes.":[69],"More":[70],"specifically,":[71],"we":[72,106],"propose":[73],"generalized":[75],"formulation":[76],"model":[81,86],"named":[82],"conditional":[83],"that,":[87],"its":[89],"process,":[91],"can":[92],"adapt":[93],"to":[94,115,127],"non-Gaussian":[95],"real":[96],"noises":[97],"estimated":[100],"signal.":[102],"In":[103],"our":[104,125],"experiments,":[105],"demonstrate":[107],"performance":[109],"proposed":[112],"approach":[113],"compared":[114],"representative":[116],"investigate":[120],"generalization":[122],"capability":[123],"other":[128],"datasets":[129],"with":[130],"noise":[131],"unseen":[133],"during":[134],"training.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":48},{"year":2025,"cited_by_count":68},{"year":2024,"cited_by_count":61},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-04-03T00:00:00"}