{"id":"https://openalex.org/W4372259784","doi":"https://doi.org/10.1109/icassp49357.2023.10095515","title":"Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","display_name":"Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259784","doi":"https://doi.org/10.1109/icassp49357.2023.10095515"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018777306","display_name":"Minki Kang","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"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Minki Kang","raw_affiliation_strings":["AITRICS","KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AITRICS","institution_ids":[]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064873387","display_name":"Dongchan Min","orcid":"https://orcid.org/0000-0002-1441-1383"},"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"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Dongchan Min","raw_affiliation_strings":["AITRICS","KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AITRICS","institution_ids":[]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070302452","display_name":"Sung Ju Hwang","orcid":"https://orcid.org/0000-0002-9675-2324"},"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"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sung Ju Hwang","raw_affiliation_strings":["AITRICS","KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AITRICS","institution_ids":[]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0981,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97255682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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":0.9962999820709229,"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":0.8017281889915466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7429230809211731},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6893223524093628},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5928272604942322},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44694846868515015},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.438609778881073},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4127196967601776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4060657024383545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017281889915466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7429230809211731},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6893223524093628},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5928272604942322},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44694846868515015},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.438609778881073},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4127196967601776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4060657024383545},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1991111872","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2892620417","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3095545636","https://openalex.org/W3110257065","https://openalex.org/W3128910262","https://openalex.org/W3168527213","https://openalex.org/W3172148458","https://openalex.org/W3196001064","https://openalex.org/W3198213150","https://openalex.org/W3204602440","https://openalex.org/W4205742757","https://openalex.org/W4225680573","https://openalex.org/W4226332109","https://openalex.org/W4320169845","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6790220310","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6802527329","https://openalex.org/W6805710207","https://openalex.org/W6849953009"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"a":[3,61,79],"significant":[4],"progress":[5],"in":[6,11,18,38],"Text-To-Speech":[7],"(TTS)":[8],"synthesis":[9],"technology":[10],"recent":[12,88],"years,":[13],"thanks":[14],"to":[15,34,74],"the":[16,40],"advancement":[17],"neural":[19],"generative":[20],"modeling.":[21],"However,":[22],"existing":[23],"methods":[24],"on":[25,60,92],"any-speaker":[26,53],"adaptive":[27,54],"TTS":[28,55,90],"have":[29],"achieved":[30],"unsatisfactory":[31],"performance,":[32],"due":[33],"their":[35],"suboptimal":[36],"accuracy":[37],"mimicking":[39],"target":[41,75],"speakers\u2019":[42,76],"styles.":[43],"In":[44],"this":[45],"work,":[46],"we":[47],"present":[48],"Grad-StyleSpeech,":[49],"which":[50],"is":[51,58],"an":[52],"framework":[56],"that":[57,64],"based":[59],"diffusion":[62],"model":[63],"can":[65],"generate":[66],"highly":[67],"natural":[68],"speech":[69],"with":[70],"extremely":[71],"high":[72],"similarity":[73],"voice,":[77],"given":[78],"few":[80],"seconds":[81],"of":[82],"reference":[83],"speech.":[84],"Grad-StyleSpeech":[85],"significantly":[86],"outperforms":[87],"speaker-adaptive":[89],"baselines":[91],"English":[93],"benchmarks.":[94],"Audio":[95],"samples":[96],"are":[97],"available":[98],"at":[99],"https://nardien.github.io/grad-stylespeech-demo.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}