{"id":"https://openalex.org/W4385488985","doi":"https://doi.org/10.1109/icasspw59220.2023.10193157","title":"A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS","display_name":"A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385488985","doi":"https://doi.org/10.1109/icasspw59220.2023.10193157"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100772861","display_name":"Siyang Wang","orcid":"https://orcid.org/0009-0004-8733-3103"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Siyang Wang","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100772861"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.6983,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75210742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T12031","display_name":"Speech and dialogue systems","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.7986757755279541},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.780340313911438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6241453886032104},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5848888158798218},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5062688589096069},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4176928997039795},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3538070619106293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33779484033584595},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10649293661117554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986757755279541},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.780340313911438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6241453886032104},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5848888158798218},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5062688589096069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4176928997039795},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3538070619106293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33779484033584595},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10649293661117554},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2901285216","https://openalex.org/W2964243274","https://openalex.org/W2972606665","https://openalex.org/W2973049979","https://openalex.org/W2973177710","https://openalex.org/W3011535310","https://openalex.org/W3016151952","https://openalex.org/W3140429000","https://openalex.org/W3150572638","https://openalex.org/W3163596720","https://openalex.org/W3196001064","https://openalex.org/W3197580070","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W4226132755","https://openalex.org/W4226380987","https://openalex.org/W4297841714","https://openalex.org/W4319862479","https://openalex.org/W4382202703","https://openalex.org/W4394671563","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Recent":[0],"work":[1,124],"has":[2],"explored":[3],"using":[4],"self-supervised":[5],"learning":[6],"(SSL)":[7],"speech":[8,32,70,130],"representations":[9],"such":[10],"as":[11,13],"wav2vec2.0":[12,108],"the":[14,35,44,52,76,103,143],"representation":[15],"medium":[16],"in":[17,21,79,117,142],"standard":[18],"two-stage":[19,80],"TTS,":[20,39,51],"place":[22],"of":[23,54,75,106,147],"conventionally":[24],"used":[25],"mel-spectrograms.":[26],"It":[27],"is":[28,34,56],"however":[29],"unclear":[30],"which":[31,55],"SSL":[33,131],"better":[36],"fit":[37],"for":[38],"and":[40,49,85,94,115,120,138],"whether":[41],"or":[42],"not":[43],"performance":[45],"differs":[46],"between":[47],"read":[48,84,119],"spontaneous":[50,86,121],"later":[53],"arguably":[57],"more":[58],"challenging.":[59],"This":[60],"study":[61],"aims":[62],"at":[63,154],"addressing":[64],"these":[65],"questions":[66],"by":[67],"testing":[68],"several":[69],"SSLs,":[71],"including":[72],"different":[73],"layers":[74],"same":[77],"SSL,":[78],"TTS":[81,91,136],"on":[82,127],"both":[83,118,128],"corpora,":[87],"while":[88],"maintaining":[89],"constant":[90],"model":[92],"architecture":[93],"training":[95],"settings.":[96],"Results":[97],"from":[98],"listening":[99],"tests":[100],"show":[101],"that":[102],"9th":[104],"layer":[105],"12-layer":[107],"(ASR":[109],"finetuned)":[110],"outperforms":[111],"other":[112],"tested":[113],"SSLs":[114,140],"mel-spectrogram,":[116],"TTS.":[122,148],"Our":[123],"sheds":[125],"light":[126],"how":[129,139],"can":[132,151],"readily":[133],"improve":[134],"current":[135],"systems,":[137],"compare":[141],"challenging":[144],"generative":[145],"task":[146],"Audio":[149],"examples":[150],"be":[152],"found":[153],"https://www.speech.kth.se/tts-demos/ssr_tts":[155]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
