{"id":"https://openalex.org/W4392902843","doi":"https://doi.org/10.1109/icassp48485.2024.10448268","title":"VoiceLDM: Text-to-Speech with Environmental Context","display_name":"VoiceLDM: Text-to-Speech with Environmental Context","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902843","doi":"https://doi.org/10.1109/icassp48485.2024.10448268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448268","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/A5035686822","display_name":"Yeonghyeon Lee","orcid":"https://orcid.org/0000-0002-3946-5660"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeonghyeon Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113607671","display_name":"Inmo Yeon","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inmo Yeon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035686822"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.8119,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84375991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12566","last_page":"12571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.998199999332428,"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":0.8660976886749268},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5832381248474121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5740298628807068},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5568973422050476},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5162680149078369},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49398642778396606},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4819047749042511},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4748535454273224},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44400885701179504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438865065574646},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4384303689002991},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2685418725013733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660976886749268},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5832381248474121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5740298628807068},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5568973422050476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5162680149078369},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49398642778396606},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4819047749042511},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4748535454273224},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44400885701179504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438865065574646},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4384303689002991},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2685418725013733},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448268","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G515828364","display_name":null,"funder_award_id":"No. RS-","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G904912805","display_name":null,"funder_award_id":"RS-2023-00222383","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W3198123658","https://openalex.org/W3205644108","https://openalex.org/W4232282348","https://openalex.org/W4312933868","https://openalex.org/W4322759846","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4375869257","https://openalex.org/W4378942405","https://openalex.org/W4381786045","https://openalex.org/W4385822787","https://openalex.org/W4387969125","https://openalex.org/W4396877837","https://openalex.org/W4398152753","https://openalex.org/W6771467084","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6840815571","https://openalex.org/W6845479124","https://openalex.org/W6847363464","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6850680583","https://openalex.org/W6852971826"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W1911859126","https://openalex.org/W2163537793","https://openalex.org/W2781555308","https://openalex.org/W4386794561","https://openalex.org/W2547068348","https://openalex.org/W2916997151","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"VoiceLDM,":[3],"a":[4,50,70],"model":[5,53],"designed":[6],"to":[7,63,102],"produce":[8],"audio":[9,90,119,136],"that":[10,112,120,156],"accurately":[11],"follows":[12],"two":[13],"distinct":[14],"natural":[15],"language":[16],"text":[17],"prompts:":[18],"the":[19,23,31,36,39,42,105,129,133,138,145],"description":[20],"prompt":[21,68],"and":[22,59,80,148,154,162],"content":[24,67],"prompt.":[25],"The":[26],"former":[27],"provides":[28],"information":[29],"about":[30],"overall":[32],"environmental":[33],"context":[34],"of":[35,88,107,116,132,152],"audio,":[37],"while":[38],"latter":[40],"conveys":[41],"linguistic":[43],"content.":[44],"To":[45],"achieve":[46],"this,":[47],"we":[48,97,143],"adopt":[49],"text-to-audio":[51,150],"(TTA)":[52],"based":[54],"on":[55,85,137],"latent":[56],"diffusion":[57],"models":[58],"extend":[60],"its":[61],"functionality":[62],"incorporate":[64],"an":[65],"additional":[66],"as":[69],"conditional":[71],"input.":[72],"By":[73],"utilizing":[74],"pretrained":[75],"contrastive":[76],"language-audio":[77],"pretraining":[78],"(CLAP)":[79],"Whisper,":[81],"VoiceLDM":[82,113,153],"is":[83,114],"trained":[84],"large":[86],"amounts":[87],"real-world":[89],"without":[91],"manual":[92],"annotations":[93],"or":[94],"transcriptions.":[95],"Additionally,":[96],"employ":[98],"dual":[99],"classifier-free":[100],"guidance":[101],"further":[103],"enhance":[104],"controllability":[106],"VoiceLDM.":[108],"Experimental":[109],"results":[110],"demonstrate":[111],"capable":[115],"generating":[117],"plausible":[118],"aligns":[121],"well":[122],"with":[123],"both":[124],"input":[125],"conditions,":[126],"even":[127],"surpassing":[128],"speech":[130],"intelligibility":[131],"ground":[134],"truth":[135],"AudioCaps":[139],"test":[140],"set.":[141],"Furthermore,":[142],"explore":[144],"text-to-speech":[146],"(TTS)":[147],"zero-shot":[149],"capabilities":[151],"show":[155],"it":[157],"achieves":[158],"competitive":[159],"results.":[160],"Demos":[161],"code":[163],"are":[164],"available":[165],"at":[166],"https://voiceldm.github.io.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
