{"id":"https://openalex.org/W4399554121","doi":"https://doi.org/10.1109/lsp.2024.3449221","title":"The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems","display_name":"The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399554121","doi":"https://doi.org/10.1109/lsp.2024.3449221"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3449221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3449221","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.06160","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":false,"raw_author_name":"Philippe Gonzalez","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0009-0006-4965-3514","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"],"raw_orcid":"https://orcid.org/0000-0001-6856-8928","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"],"raw_orcid":"https://orcid.org/0000-0002-3724-6114","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"],"raw_orcid":"https://orcid.org/0000-0003-1478-622X","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"],"raw_orcid":"https://orcid.org/0000-0003-0941-3146","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"],"raw_orcid":"https://orcid.org/0000-0002-5463-5509","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6861,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84320673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2225","last_page":"2229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9580000042915344,"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/discriminative-model","display_name":"Discriminative model","score":0.8363165855407715},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7008693814277649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5854671001434326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5550560355186462},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.542488157749176},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5305072665214539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39575615525245667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3259105682373047},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07816219329833984},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06907588243484497}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8363165855407715},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7008693814277649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5854671001434326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5550560355186462},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.542488157749176},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5305072665214539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39575615525245667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3259105682373047},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07816219329833984},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06907588243484497},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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":4,"locations":[{"id":"doi:10.1109/lsp.2024.3449221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3449221","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2406.06160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.06160","pdf_url":"https://arxiv.org/pdf/2406.06160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire/ec0b1635-9ea4-45e0-8c26-72071f5542ac","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/ec0b1635-9ea4-45e0-8c26-72071f5542ac","pdf_url":"https://vbn.aau.dk/ws/files/762478313/The_Effect_of_Training_Dataset_Size_on_Discriminative_and_Diffusion-Based_Speech_Enhancement_Systems.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gonzalez, P, Tan, Z H, Ostergaard, J, Jensen, J, Alstrom, T S & May, T 2024, 'The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems', IEEE Signal Processing Letters, vol. 31, 10645209, pp. 2225-2229. https://doi.org/10.1109/LSP.2024.3449221","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.atira.dk:publications/150e25ba-8e44-463f-8602-103e94a78815","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/150e25ba-8e44-463f-8602-103e94a78815","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Gonzalez , P , Tan , Z H , Ostergaard , J , Jensen , J , Alstrom , T S &amp; May , T 2024 , ' The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems ' , IEEE Signal Processing Letters , vol. 31 , pp. 2225-2229 . https://doi.org/10.1109/LSP.2024.3449221","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.06160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.06160","pdf_url":"https://arxiv.org/pdf/2406.06160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399554121.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1967300041","https://openalex.org/W1974387177","https://openalex.org/W1991646723","https://openalex.org/W2024490156","https://openalex.org/W2040782121","https://openalex.org/W2044893557","https://openalex.org/W2054480978","https://openalex.org/W2094721231","https://openalex.org/W2114218864","https://openalex.org/W2168379380","https://openalex.org/W2199505332","https://openalex.org/W2364134690","https://openalex.org/W2516001803","https://openalex.org/W2952218014","https://openalex.org/W2961183107","https://openalex.org/W2962866211","https://openalex.org/W3015969340","https://openalex.org/W3096408984","https://openalex.org/W3103003256","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/W4372266968","https://openalex.org/W4372268522","https://openalex.org/W4372347392","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4392903364","https://openalex.org/W4392903897","https://openalex.org/W4392910516","https://openalex.org/W4392931780","https://openalex.org/W6679045638","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6798721538","https://openalex.org/W6802938626","https://openalex.org/W6803075754","https://openalex.org/W6851069163","https://openalex.org/W6852134528","https://openalex.org/W6859566461","https://openalex.org/W6967306011"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"The":[0],"performance":[1,29,86,109,179],"of":[2,22,69,103,110,133,146,165,170,205],"deep":[3],"neural":[4],"network-based":[5],"speech":[6,27,59,116,134],"enhancement":[7,28,60,117],"systems":[8,118,154,162,202],"typically":[9,43],"increases":[10],"with":[11,45,168,203],"the":[12,20,67,77,85,91,101,108,125,152,156,160,185,192,200],"training":[13,23,70,104,186],"dataset":[14,24,71,93,105,187],"size.":[15],"However,":[16,175],"studies":[17,64],"that":[18,65,151],"investigated":[19,66],"effect":[21,68,102],"size":[25,72,94,106,188],"on":[26,107],"did":[30,73],"not":[31,74,181],"consider":[32],"recent":[33],"approaches,":[34],"such":[35],"as":[36,189,191],"diffusion-based":[37,115,153],"generative":[38],"models.":[39],"Diffusion":[40],"models":[41],"are":[42,197],"trained":[44],"massive":[46],"datasets":[47,145,169,204],"for":[48,58,76,124],"image":[49],"generation":[50],"tasks,":[51],"but":[52],"whether":[53,84],"this":[54],"is":[55,61,81],"also":[56],"required":[57],"unknown.":[62],"Moreover,":[63],"control":[75,123],"data":[78,126],"diversity.":[79,96],"It":[80],"thus":[82],"unclear":[83],"improvement":[87],"was":[88],"due":[89],"to":[90,143,159],"increased":[92],"or":[95,173,208],"Therefore,":[97],"we":[98],"systematically":[99],"investigate":[100],"popular":[111],"state-of-the-art":[112],"discriminative":[113,161,193,201],"and":[114,138,195],"in":[119,163],"matched":[120],"conditions.":[121],"We":[122,149],"diversity":[127],"by":[128,199],"using":[129],"a":[130],"fixed":[131],"set":[132],"utterances,":[135],"noise":[136],"segments":[137],"binaural":[139],"room":[140],"impulse":[141],"responses":[142],"generate":[144],"different":[147],"sizes.":[148],"find":[150],"perform":[155],"best":[157],"relative":[158],"terms":[164],"objective":[166,177],"metrics":[167,178],"10":[171],"h":[172,207],"less.":[174],"their":[176],"does":[180],"improve":[182],"when":[183],"increasing":[184],"much":[190],"systems,":[194],"they":[196],"outperformed":[198],"100":[206],"more.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}
