{"id":"https://openalex.org/W4372349107","doi":"https://doi.org/10.1109/icassp49357.2023.10096797","title":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","display_name":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349107","doi":"https://doi.org/10.1109/icassp49357.2023.10096797"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096797","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/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Jia","raw_affiliation_strings":["Tomato AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomato AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-Cheng Chiu","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5735,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95890741,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9979000091552734,"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/speech-translation","display_name":"Speech translation","score":0.8485704660415649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8390233516693115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6791826486587524},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6309942603111267},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6086008548736572},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.579901397228241},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5608536005020142},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5478413701057434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313853621482849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5182971358299255},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5040825605392456}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8485704660415649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390233516693115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6791826486587524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6309942603111267},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6086008548736572},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.579901397228241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5608536005020142},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5478413701057434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313853621482849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5182971358299255},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5040825605392456},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096797","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":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W60702959","https://openalex.org/W1533861849","https://openalex.org/W2752796333","https://openalex.org/W2842511635","https://openalex.org/W2928941594","https://openalex.org/W2963799213","https://openalex.org/W2972495969","https://openalex.org/W3007068036","https://openalex.org/W3026041220","https://openalex.org/W3036601975","https://openalex.org/W3037465386","https://openalex.org/W3094502228","https://openalex.org/W3142316150","https://openalex.org/W3175871055","https://openalex.org/W3180374548","https://openalex.org/W3186200218","https://openalex.org/W3207738474","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4221153524","https://openalex.org/W4221155340","https://openalex.org/W4221161761","https://openalex.org/W4226033575","https://openalex.org/W4226444650","https://openalex.org/W4280601369","https://openalex.org/W4281789500","https://openalex.org/W4285181910","https://openalex.org/W4287072252","https://openalex.org/W4287848452","https://openalex.org/W4287854499","https://openalex.org/W4296069143","https://openalex.org/W4296070387","https://openalex.org/W4297808394","https://openalex.org/W4388277788","https://openalex.org/W6631943919","https://openalex.org/W6760633627","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6802857679","https://openalex.org/W6810259195","https://openalex.org/W6810673746","https://openalex.org/W6810701745","https://openalex.org/W6838789019","https://openalex.org/W6841035593"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4390516098","https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2181948922","https://openalex.org/W2883671469","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Research":[0],"on":[1,41,71,146],"speech-to-speech":[2],"translation":[3,30,139],"(S2ST)":[4],"has":[5],"progressed":[6],"rapidly":[7],"in":[8,98],"recent":[9],"years.":[10],"Many":[11],"end-to-end":[12,37,78],"systems":[13,38],"have":[14],"been":[15],"proposed":[16,102,136],"and":[17,31],"show":[18],"advantages":[19],"over":[20],"conventional":[21],"cascade":[22],"systems,":[23],"which":[24,47,68,112],"are":[25,113],"often":[26],"composed":[27],"of":[28,36,87],"recognition,":[29],"synthesis":[32],"sub-systems.":[33],"However,":[34],"most":[35],"still":[39],"rely":[40],"intermediate":[42],"textual":[43,84],"supervision":[44],"during":[45],"training,":[46],"makes":[48],"it":[49,164],"infeasible":[50],"to":[51],"work":[52],"for":[53,75,132],"languages":[54],"without":[55,82],"written":[56],"forms.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"propose":[62],"a":[63,122],"novel":[64],"model,":[65],"Textless":[66],"Translatotron,":[67],"is":[69,130],"based":[70],"Translatotron":[72,99,144],"2":[73,145],"[1],":[74],"training":[76,89],"an":[77,91,105],"direct":[79],"S2ST":[80],"model":[81,103,137,170],"any":[83],"supervision.":[85],"Instead":[86],"jointly":[88],"with":[90,126,143],"auxiliary":[92,106],"task":[93,107],"predicting":[94,108],"target":[95],"phonemes":[96],"as":[97,152,154],"2,":[100],"the":[101,135,147,155,162,166],"uses":[104],"discrete":[109],"speech":[110,119,123,128],"representations":[111],"obtained":[114],"from":[115],"learned":[116],"or":[117],"random":[118],"quantizers.":[120],"When":[121],"encoder":[124],"pre-trained":[125],"unsupervised":[127],"data":[129],"used":[131],"both":[133],"models,":[134],"obtains":[138],"quality":[140],"nearly":[141],"on-par":[142],"multilingual":[148],"CVSS-C":[149],"corpus":[150,159],"[2]":[151],"well":[153],"bilingual":[156],"Fisher":[157],"Spanish-English":[158],"[3].":[160],"On":[161],"latter,":[163],"outperforms":[165],"prior":[167],"state-of-the-art":[168],"textless":[169],"by":[171],"+18.5":[172],"BLEU.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}