{"id":"https://openalex.org/W4406858798","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849051","title":"LDMSE: Low Computational Cost Generative Diffusion Model for Speech Enhancement","display_name":"LDMSE: Low Computational Cost Generative Diffusion Model for Speech Enhancement","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858798","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849051"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Yuki Nishi","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Nishi","raw_affiliation_strings":["Tokyo Institute of Technology,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Tokyo","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokyo Institute of Technology,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Tokyo","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Iwano","raw_affiliation_strings":["Tokyo City University,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo City University,Tokyo","institution_ids":["https://openalex.org/I185088104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27213949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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":0.7422888875007629},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5630077123641968},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5060970187187195},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47998926043510437},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46587511897087097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3977864980697632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2922379672527313},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07737576961517334},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06067848205566406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422888875007629},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5630077123641968},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5060970187187195},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47998926043510437},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46587511897087097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3977864980697632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2922379672527313},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07737576961517334},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06067848205566406},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1991111872","https://openalex.org/W2094721231","https://openalex.org/W2125838338","https://openalex.org/W2128653836","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2774389566","https://openalex.org/W2964058413","https://openalex.org/W3197912330","https://openalex.org/W4206740920","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4297841790","https://openalex.org/W4312933868","https://openalex.org/W4375869198","https://openalex.org/W4380434618","https://openalex.org/W6640963894","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6796588791","https://openalex.org/W6810590380","https://openalex.org/W6843677495","https://openalex.org/W6849109464"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Recently,":[0],"a":[1,20,31,57],"generative":[2],"model":[3,6],"called":[4,33],"diffusion":[5,72],"has":[7,19],"attracted":[8],"attention.":[9],"Compared":[10],"to":[11,56],"GANs,":[12],"it":[13],"can":[14],"be":[15],"trained":[16],"stably":[17],"but":[18],"high":[21],"computational":[22,35,47],"cost":[23,36,48],"in":[24,66,96],"the":[25,67,71,82,86],"generation":[26,87],"stage.":[27],"This":[28],"paper":[29],"proposes":[30],"method":[32,84],"Low":[34],"Generative":[37],"Diffusion":[38],"Model":[39],"for":[40],"Speech":[41],"Enhancement":[42],"(LDMSE).":[43],"It":[44],"reduces":[45],"its":[46],"with":[49],"comparable":[50],"quality":[51],"by":[52,89],"compressing":[53],"speech":[54,97],"signals":[55],"latent":[58,68],"space":[59,69],"using":[60,70,77],"an":[61],"autoencoder":[62],"and":[63,79],"removing":[64],"noise":[65],"model.":[73],"In":[74],"our":[75],"evaluation":[76],"VOICBANK-DEMAND":[78],"WSJ0-CHiME3":[80],"datasets,":[81],"proposed":[83],"reduced":[85],"time":[88],"more":[90],"than":[91],"35%":[92],"without":[93],"any":[94],"degradation":[95],"quality.":[98]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}