{"id":"https://openalex.org/W4391021739","doi":"https://doi.org/10.1109/asru57964.2023.10389791","title":"Transduce and Speak: Neural Transducer for Text-To-Speech with Semantic Token Prediction","display_name":"Transduce and Speak: Neural Transducer for Text-To-Speech with Semantic Token Prediction","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021739","doi":"https://doi.org/10.1109/asru57964.2023.10389791"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040382938","display_name":"Dongjune Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongjune Lee","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027616639"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.8758,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88842074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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":0.7731084823608398},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.676059365272522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5960292816162109},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5953620672225952},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5832135677337646},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5484212636947632},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.46074190735816956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4281888008117676},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4134995937347412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3503530025482178},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20095616579055786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10033425688743591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731084823608398},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.676059365272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5960292816162109},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5953620672225952},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5832135677337646},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5484212636947632},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.46074190735816956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4281888008117676},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4134995937347412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3503530025482178},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20095616579055786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10033425688743591},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2964243274","https://openalex.org/W2970079483","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3167533889","https://openalex.org/W3198429080","https://openalex.org/W3213604094","https://openalex.org/W4221166168","https://openalex.org/W4283700324","https://openalex.org/W4311000453","https://openalex.org/W4313679638","https://openalex.org/W4390075359","https://openalex.org/W6638749077","https://openalex.org/W6766849269","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6804171790","https://openalex.org/W6847363464","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"We":[0,11,119],"introduce":[1],"a":[2,8,27,53,61],"text-to-speech":[3],"(TTS)":[4],"framework":[5,33,68],"based":[6],"on":[7,81,95],"neural":[9,28,49,137],"transducer.":[10],"use":[12],"discretized":[13],"semantic":[14,45,58],"tokens":[15,46,59],"acquired":[16],"from":[17,56],"wav2vec":[18],"2.0":[19],"embeddings,":[20],"which":[21],"makes":[22],"it":[23],"easy":[24],"to":[25,79],"adopt":[26],"transducer":[29,138],"for":[30,139],"the":[31,48,57,70,96,102,106,122,133,136],"TTS":[32,74,99,140],"enjoying":[34],"its":[35],"monotonic":[36],"alignment":[37,85],"constraints.":[38],"The":[39],"proposed":[40,103,130],"model":[41,104],"first":[42],"generates":[43],"aligned":[44],"using":[47,60],"transducer,":[50],"then":[51],"synthesizes":[52],"speech":[54,64,109],"sample":[55],"non-autoregressive":[62],"(NAR)":[63],"generator.":[65],"This":[66],"decoupled":[67],"alleviates":[69],"training":[71],"complexity":[72],"of":[73,128,135],"and":[75,84,87,111,116,125],"allows":[76],"each":[77],"stage":[78],"focus":[80],"1)":[82],"linguistic":[83],"modeling":[86],"2)":[88],"fine-grained":[89],"acoustic":[90],"modeling,":[91],"respectively.":[92],"Experimental":[93],"results":[94],"zero-shot":[97],"adaptive":[98],"show":[100],"that":[101],"exceeds":[105],"baselines":[107],"in":[108],"quality":[110],"speaker":[112],"similarity":[113],"via":[114],"objective":[115],"subjective":[117],"measures.":[118],"also":[120],"investigate":[121],"inference":[123],"speed":[124],"prosody":[126],"controllability":[127],"our":[129],"model,":[131],"showing":[132],"potential":[134],"frameworks.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}