{"id":"https://openalex.org/W4406858747","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849285","title":"Enhancing Neural Speech Embeddings for Generative Speech Models","display_name":"Enhancing Neural Speech Embeddings for Generative Speech Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858747","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849285"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849285","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01JRA5F1P4Y7CF2ZXWMXW9D03V/file/01JRA5FP4039GHA999JS4HBGG0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100652831","display_name":"Doyeon Kim","orcid":"https://orcid.org/0000-0002-6484-8575"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doyeon Kim","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007667052","display_name":"Yanjue Song","orcid":"https://orcid.org/0000-0002-9684-6611"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yanjue Song","raw_affiliation_strings":["IDLab, Ghent University - imec,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Ghent University - imec,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["IDLab, Ghent University - imec,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Ghent University - imec,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Eng.,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29319171,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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/T12031","display_name":"Speech and dialogue systems","score":0.9387000203132629,"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/T10028","display_name":"Topic Modeling","score":0.925000011920929,"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":0.7396261692047119},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6259797215461731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5695227384567261},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4431169927120209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40118321776390076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34775233268737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396261692047119},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6259797215461731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5695227384567261},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4431169927120209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40118321776390076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34775233268737793}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849285","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"},{"id":"pmh:oai:archive.ugent.be:01JRA5F1P4Y7CF2ZXWMXW9D03V","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01JRA5F1P4Y7CF2ZXWMXW9D03V","pdf_url":"https://biblio.ugent.be/publication/01JRA5F1P4Y7CF2ZXWMXW9D03V/file/01JRA5FP4039GHA999JS4HBGG0.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798350367331","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01JRA5F1P4Y7CF2ZXWMXW9D03V","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01JRA5F1P4Y7CF2ZXWMXW9D03V","pdf_url":"https://biblio.ugent.be/publication/01JRA5F1P4Y7CF2ZXWMXW9D03V/file/01JRA5FP4039GHA999JS4HBGG0.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798350367331","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321314","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406858747.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W1597121597","https://openalex.org/W1974387177","https://openalex.org/W2555915854","https://openalex.org/W2593116425","https://openalex.org/W2696967604","https://openalex.org/W2787894218","https://openalex.org/W3041561163","https://openalex.org/W3161480375","https://openalex.org/W3191448984","https://openalex.org/W3196475561","https://openalex.org/W3197042120","https://openalex.org/W3197273793","https://openalex.org/W3197580070","https://openalex.org/W3207860153","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224933800","https://openalex.org/W4226403810","https://openalex.org/W4232282348","https://openalex.org/W4312095873","https://openalex.org/W4372266927","https://openalex.org/W4386764866","https://openalex.org/W4392909571","https://openalex.org/W4392944340","https://openalex.org/W6746278845","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6838843145","https://openalex.org/W6853937136"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W3204019825","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"We":[0,84],"explore":[1],"a":[2,26,55,98,103],"speech":[3,8,73],"enhancement":[4,71],"framework":[5],"where":[6],"neural":[7,27,43,120],"embeddings,":[9],"derived":[10],"from":[11,93],"pre-trained":[12],"self-supervised":[13],"learning":[14],"(SSL)":[15],"models":[16],"applied":[17],"to":[18,25,29,45,101],"noisy":[19],"signals,":[20],"are":[21],"used":[22],"as":[23],"inputs":[24],"vocoder":[28,109],"generate":[30],"the":[31,59,64,75,87,94,108,119,125],"corresponding":[32],"clean":[33],"speech.":[34],"The":[35],"primary":[36],"innovation":[37],"lies":[38],"in":[39,54,81,97,132],"enhancing":[40],"these":[41],"latent":[42],"embeddings":[44],"mitigate":[46],"distortions":[47],"caused":[48],"by":[49],"noise":[50,137],"and":[51,72,138],"reverberation,":[52],"resulting":[53],"superior":[56],"quality":[57],"of":[58,89,127],"synthesized":[60],"signal.":[61],"By":[62],"dividing":[63],"process":[65],"into":[66],"Separate":[67],"phases":[68],"for":[69,78,107,117],"embedding":[70,106],"generation,":[74],"approach":[76],"allows":[77],"greater":[79],"flexibility":[80],"network":[82],"design.":[83],"also":[85],"examine":[86],"advantage":[88],"integrating":[90],"hidden":[91],"states":[92],"SSL":[95],"model":[96],"learnable":[99],"manner":[100],"create":[102],"more":[104],"robust":[105],"input.":[110],"Additionally,":[111],"we":[112],"investigate":[113],"various":[114],"loss":[115],"functions":[116],"training":[118],"vocoder.":[121],"Experimental":[122],"results":[123],"confirm":[124],"effectiveness":[126],"our":[128],"proposed":[129],"approach,":[130],"particularly":[131],"environments":[133],"with":[134],"simultaneous":[135],"background":[136],"reverberation.":[139]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}