{"id":"https://openalex.org/W4392910516","doi":"https://doi.org/10.1109/icassp48485.2024.10446610","title":"Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler","display_name":"Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910516","doi":"https://doi.org/10.1109/icassp48485.2024.10446610"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446610","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/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":false,"raw_author_name":"Philippe Gonzalez","raw_affiliation_strings":["Technical University of Denmark,Department of Health Technology","Department of Health Technology, Technical University of Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Health Technology","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Health Technology, Technical University of 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":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, 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":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, 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":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, 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":["Technical University of Denmark,Department of Applied Mathematics and Computer Science","Department of Applied Mathematics and Computer Science, Technical University of Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Applied Mathematics and Computer Science","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of 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":["Technical University of Denmark,Department of Health Technology","Department of Health Technology, Technical University of Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Health Technology","institution_ids":["https://openalex.org/I96673099"]},{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6893,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8371166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10431","last_page":"10435"},"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":0.998199999332428,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7442256212234497},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7192734479904175},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6793683767318726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5873528718948364},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5315620303153992},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5307030081748962},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4714330732822418},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4506880044937134},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43588489294052124},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4186393618583679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34566783905029297},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24559971690177917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1666262447834015},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06497830152511597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442256212234497},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7192734479904175},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6793683767318726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5873528718948364},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5315620303153992},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5307030081748962},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4714330732822418},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4506880044937134},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43588489294052124},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4186393618583679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34566783905029297},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24559971690177917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1666262447834015},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06497830152511597},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446610","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"},{"id":"pmh:oai:pure.atira.dk:publications/37698343-c282-4b58-9d92-4aebede60aeb","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/37698343-c282-4b58-9d92-4aebede60aeb","pdf_url":null,"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":null,"license_id":null,"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, Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler. in 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (Institute of Electrical and Electronics Engineers), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 10431-10435, 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, Seoul, Korea, Republic of, 14/04/2024. https://doi.org/10.1109/ICASSP48485.2024.10446610","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W1991111872","https://openalex.org/W2024490156","https://openalex.org/W2054480978","https://openalex.org/W2094721231","https://openalex.org/W2114218864","https://openalex.org/W2199505332","https://openalex.org/W2289394825","https://openalex.org/W2514828952","https://openalex.org/W2516001803","https://openalex.org/W2559260703","https://openalex.org/W2952218014","https://openalex.org/W2961183107","https://openalex.org/W2962866211","https://openalex.org/W3035790469","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3120954100","https://openalex.org/W4213196139","https://openalex.org/W4221144097","https://openalex.org/W4225309689","https://openalex.org/W4232282348","https://openalex.org/W4297841790","https://openalex.org/W4312933868","https://openalex.org/W4372266968","https://openalex.org/W4372268522","https://openalex.org/W4372349390","https://openalex.org/W4375869120","https://openalex.org/W4375869169","https://openalex.org/W4380434618","https://openalex.org/W4387010482","https://openalex.org/W6631190155","https://openalex.org/W6679045638","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/W6798721538","https://openalex.org/W6802938626","https://openalex.org/W6803075754","https://openalex.org/W6810793953","https://openalex.org/W6838452192","https://openalex.org/W6849109464","https://openalex.org/W6849744127","https://openalex.org/W6851069163"],"related_works":["https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W3002068412","https://openalex.org/W1585241115","https://openalex.org/W2120213246","https://openalex.org/W3171883019","https://openalex.org/W1564179349"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,8,163],"are":[2],"a":[3,39,100,126,130,174,181,187],"new":[4],"class":[5],"of":[6,78,99],"generative":[7],"that":[9,132,143,173],"have":[10,20,133],"recently":[11],"been":[12,135],"applied":[13,136],"to":[14,29,117,137,160,186],"speech":[15,71,102,138,192],"enhancement":[16,103,139],"successfully.":[17],"Previous":[18],"works":[19],"demonstrated":[21],"their":[22],"superior":[23,157,178],"performance":[24,98,158,179],"in":[25,164],"mismatched":[26,119,168],"conditions":[27],"compared":[28,159,185],"state-of-the":[30],"art":[31],"discriminative":[32,162],"models.":[33],"However,":[34],"this":[35,91],"was":[36],"investigated":[37],"with":[38,125],"single":[40],"database":[41],"for":[42,47,70,153,191],"training":[43],"and":[44,110,129,155,167],"another":[45],"one":[46],"testing,":[48],"which":[49],"makes":[50],"the":[51,56,63,83,87,96,144],"results":[52],"highly":[53],"dependent":[54],"on":[55],"particular":[57],"databases.":[58],"Moreover,":[59],"recent":[60],"developments":[61],"from":[62,149],"image":[64],"generation":[65],"literature":[66],"remain":[67],"largely":[68],"unexplored":[69],"enhancement.":[72,193],"These":[73],"include":[74],"several":[75],"design":[76],"aspects":[77],"diffusion":[79],"models,":[80],"such":[81],"as":[82],"noise":[84,109,127],"schedule":[85,128],"or":[86],"reverse":[88],"sampler.":[89],"In":[90],"work,":[92],"we":[93],"systematically":[94],"assess":[95],"generalization":[97],"diffusion-based":[101],"model":[104],"by":[105],"using":[106,150],"multiple":[107,151],"speech,":[108],"binaural":[111],"room":[112],"impulse":[113],"response":[114],"(BRIR)":[115],"databases":[116,152],"simulate":[118],"acoustic":[120],"conditions.":[121,169],"We":[122,141,170],"also":[123,171],"experiment":[124],"sampler":[131,176,188],"not":[134],"before.":[140],"show":[142,172],"proposed":[145],"system":[146],"substantially":[147],"benefits":[148],"training,":[154],"achieves":[156,177],"state-of-the-art":[161],"both":[165],"matched":[166],"Heun-based":[175],"at":[180],"smaller":[182],"computational":[183],"cost":[184],"commonly":[189],"used":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
