{"id":"https://openalex.org/W4403095773","doi":"https://doi.org/10.1109/taslp.2024.3473319","title":"Investigating the Design Space of Diffusion Models for Speech Enhancement","display_name":"Investigating the Design Space of Diffusion Models for Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403095773","doi":"https://doi.org/10.1109/taslp.2024.3473319"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3473319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3473319","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/768416526/Investigating_the_Design_Space_of_Diffusion_Models_for_Speech_Enhancement.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103167575","display_name":"Philippe Gonzalez","orcid":"https://orcid.org/0009-0006-4965-3514"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Philippe Gonzalez","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894109","display_name":"Jan \u00d8stergaard","orcid":"https://orcid.org/0000-0002-3724-6114"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jan \u00d8stergaard","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064146030","display_name":"Tommy Sonne Alstr\u00f8m","orcid":"https://orcid.org/0000-0003-0941-3146"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tommy Sonne Alstr\u00f8m","raw_affiliation_strings":["Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103167575"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":5.2565,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.96540931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"4486","last_page":"4500"},"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":0.9969000220298767,"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":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6383270621299744},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5970662832260132},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5297977328300476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43044331669807434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34312739968299866},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22093313932418823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10647177696228027},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07021734118461609}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6383270621299744},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5970662832260132},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5297977328300476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43044331669807434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34312739968299866},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22093313932418823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10647177696228027},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07021734118461609},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3473319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3473319","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/cf9812b7-2ebb-42b6-bd3b-bf685295ebc8","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/cf9812b7-2ebb-42b6-bd3b-bf685295ebc8","pdf_url":"https://vbn.aau.dk/ws/files/768416526/Investigating_the_Design_Space_of_Diffusion_Models_for_Speech_Enhancement.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gonzalez, P, Tan, Z-H, \u00d8stergaard, J, Jensen, J, Alstr\u00f8m, T S & May, T 2024, 'Investigating the Design Space of Diffusion Models for Speech Enhancement', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 4486-4500. https://doi.org/10.1109/TASLP.2024.3473319","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/cf9812b7-2ebb-42b6-bd3b-bf685295ebc8","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/cf9812b7-2ebb-42b6-bd3b-bf685295ebc8","pdf_url":"https://vbn.aau.dk/ws/files/768416526/Investigating_the_Design_Space_of_Diffusion_Models_for_Speech_Enhancement.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gonzalez, P, Tan, Z-H, \u00d8stergaard, J, Jensen, J, Alstr\u00f8m, T S & May, T 2024, 'Investigating the Design Space of Diffusion Models for Speech Enhancement', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 4486-4500. https://doi.org/10.1109/TASLP.2024.3473319","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403095773.pdf","grobid_xml":"https://content.openalex.org/works/W4403095773.grobid-xml"},"referenced_works_count":104,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1505878979","https://openalex.org/W1901129140","https://openalex.org/W1967300041","https://openalex.org/W1974387177","https://openalex.org/W1991111872","https://openalex.org/W1991646723","https://openalex.org/W1997836753","https://openalex.org/W2013035813","https://openalex.org/W2017957151","https://openalex.org/W2024490156","https://openalex.org/W2035576074","https://openalex.org/W2044063703","https://openalex.org/W2044893557","https://openalex.org/W2054480978","https://openalex.org/W2064675550","https://openalex.org/W2094721231","https://openalex.org/W2096554907","https://openalex.org/W2114218864","https://openalex.org/W2130283666","https://openalex.org/W2166817508","https://openalex.org/W2199505332","https://openalex.org/W2514828952","https://openalex.org/W2516001803","https://openalex.org/W2746457594","https://openalex.org/W2766672686","https://openalex.org/W2804382237","https://openalex.org/W2952218014","https://openalex.org/W2961183107","https://openalex.org/W2962866211","https://openalex.org/W2963587345","https://openalex.org/W2972436155","https://openalex.org/W3004970274","https://openalex.org/W3011982609","https://openalex.org/W3015199127","https://openalex.org/W3015312544","https://openalex.org/W3015338123","https://openalex.org/W3027637851","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3120954100","https://openalex.org/W4211127940","https://openalex.org/W4213196139","https://openalex.org/W4221144097","https://openalex.org/W4225309689","https://openalex.org/W4232282348","https://openalex.org/W4289752563","https://openalex.org/W4297841790","https://openalex.org/W4303440777","https://openalex.org/W4312756164","https://openalex.org/W4312933868","https://openalex.org/W4372266968","https://openalex.org/W4372268522","https://openalex.org/W4372341905","https://openalex.org/W4372347392","https://openalex.org/W4372349390","https://openalex.org/W4375869120","https://openalex.org/W4375869169","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822703","https://openalex.org/W4385822783","https://openalex.org/W4385822788","https://openalex.org/W4385822821","https://openalex.org/W4385823353","https://openalex.org/W4386764055","https://openalex.org/W4387010482","https://openalex.org/W4392903364","https://openalex.org/W4392903897","https://openalex.org/W4392910516","https://openalex.org/W4392931780","https://openalex.org/W4393776813","https://openalex.org/W4393792386","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6738884980","https://openalex.org/W6762871372","https://openalex.org/W6777701575","https://openalex.org/W6778946027","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6788990321","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6797906067","https://openalex.org/W6798721538","https://openalex.org/W6802938626","https://openalex.org/W6803075754","https://openalex.org/W6809884996","https://openalex.org/W6809940947","https://openalex.org/W6810793953","https://openalex.org/W6838452192","https://openalex.org/W6839052650","https://openalex.org/W6840561836","https://openalex.org/W6844364769","https://openalex.org/W6845281891","https://openalex.org/W6849109464","https://openalex.org/W6849744127","https://openalex.org/W6851069163","https://openalex.org/W6967306011"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,8,27,41,136],"are":[2],"a":[3,19,48,75,198,212,229],"new":[4],"class":[5],"of":[6,134,162,174,201,231],"generative":[7],"that":[9,137,171,197],"have":[10,22],"shown":[11],"outstanding":[12],"performance":[13,173],"in":[14,38,46,66,165],"image":[15,67,125],"generation":[16,68,126],"literature.":[17],"As":[18],"consequence,":[20],"studies":[21],"attempted":[23],"to":[24,28,42,104,120,129,183,210],"apply":[25,121],"diffusion":[26,40,61,94,135],"other":[29],"tasks,":[30],"such":[31,74,144],"as":[32,145],"speech":[33,43,56,88,115,142,177,192,215],"enhancement.":[34],"A":[35],"popular":[36,60,213],"approach":[37],"adapting":[39],"enhancement":[44,89,178,216],"consists":[45],"modelling":[47],"progressive":[49,108,185],"transformation":[50,76,109,186],"between":[51,110,187],"the":[52,78,85,92,107,111,146,150,154,160,166,172,184,188,225],"clean":[53,112,189],"and":[54,113,128,190,207],"noisy":[55,114,191],"signals.":[57,116,193],"However,":[58],"one":[59],"model":[62,95],"framework":[63,103],"previously":[64],"laid":[65],"literature":[69],"did":[70],"not":[71],"account":[72,105],"for":[73,106,141],"towards":[77],"system":[79,217],"input,":[80],"which":[81],"prevents":[82],"from":[83,124],"relating":[84],"existing":[86],"diffusion-based":[87,176,214],"systems":[90,179],"with":[91],"aforementioned":[93],"framework.":[96],"To":[97],"address":[98],"this,":[99],"we":[100,195],"extend":[101],"this":[102],"This":[117],"allows":[118,209],"us":[119],"recent":[122],"developments":[123],"literature,":[127],"systematically":[130],"investigate":[131],"design":[132],"aspects":[133],"remain":[138],"largely":[139],"unexplored":[140],"enhancement,":[143],"neural":[147],"network":[148],"preconditioning,":[149,202],"training":[151,203],"loss":[152,204],"weighting,":[153,205],"stochastic":[155],"differential":[156],"equation":[157],"(SDE),":[158],"or":[159],"amount":[161],"stochasticity":[163],"injected":[164],"reverse":[167],"process.":[168],"We":[169],"show":[170,196],"previous":[175],"cannot":[180],"be":[181],"attributed":[182],"Moreover,":[194],"proper":[199],"choice":[200],"SDE":[206],"sampler":[208],"outperform":[211],"while":[218],"using":[219],"fewer":[220],"sampling":[221],"steps,":[222],"thus":[223],"reducing":[224],"computational":[226],"cost":[227],"by":[228],"factor":[230],"four.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}