{"id":"https://openalex.org/W4408352084","doi":"https://doi.org/10.1109/icassp49660.2025.10889740","title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","display_name":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352084","doi":"https://doi.org/10.1109/icassp49660.2025.10889740"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5057816329","display_name":"Jinzheng Zhao","orcid":"https://orcid.org/0009-0004-3910-850X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinzheng Zhao","raw_affiliation_strings":["University of Surrey,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013781881","display_name":"Niko Moritz","orcid":"https://orcid.org/0000-0003-4352-8115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045428440","display_name":"Egor Lakomkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Egor Lakomkin","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004148531","display_name":"Ruiming Xie","orcid":"https://orcid.org/0009-0003-8315-7491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiming Xie","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085174046","display_name":"Zhiping Xiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiping Xiu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101531206","display_name":"Zeeshan Ahmed","orcid":"https://orcid.org/0000-0002-3736-3484"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeeshan Ahmed","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075098210","display_name":"Duc Minh Le","orcid":"https://orcid.org/0000-0001-7654-1127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9929999709129333,"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":0.9929999709129333,"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":0.9839000105857849,"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":0.9531000256538391,"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":0.8062556982040405},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7626307606697083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6210739612579346},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.5225733518600464},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5011448860168457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4937921464443207},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49224939942359924},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47436341643333435},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45712560415267944},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.40261733531951904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35725826025009155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062556982040405},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7626307606697083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6210739612579346},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5225733518600464},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5011448860168457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4937921464443207},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49224939942359924},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47436341643333435},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45712560415267944},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.40261733531951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35725826025009155},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2136545725","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W3095410713","https://openalex.org/W3115075512","https://openalex.org/W3162665866","https://openalex.org/W3180374548","https://openalex.org/W3196509775","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213993043","https://openalex.org/W3215615641","https://openalex.org/W4226033575","https://openalex.org/W4287854499","https://openalex.org/W4307323391","https://openalex.org/W4372349107","https://openalex.org/W4385570550","https://openalex.org/W4385823495","https://openalex.org/W4402671605","https://openalex.org/W6780218876","https://openalex.org/W6810673746","https://openalex.org/W6810701745","https://openalex.org/W6838789019","https://openalex.org/W6841035593","https://openalex.org/W6849105126","https://openalex.org/W6850218400","https://openalex.org/W6852381208","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6853998256","https://openalex.org/W6855401507","https://openalex.org/W6868956406"],"related_works":["https://openalex.org/W2338806053","https://openalex.org/W4200068392","https://openalex.org/W2184371793","https://openalex.org/W2537969829","https://openalex.org/W596245619","https://openalex.org/W2909367404","https://openalex.org/W4388404911","https://openalex.org/W2251328660","https://openalex.org/W2565668967","https://openalex.org/W1516264999"],"abstract_inverted_index":{"Cascaded":[0],"speech-to-speech":[1],"translation":[2,33,58,117],"systems":[3],"often":[4],"suffer":[5],"from":[6],"the":[7,48,98,104,133],"error":[8],"accumulation":[9],"problem":[10],"and":[11,60,91,111,124],"high":[12],"latency,":[13,123],"which":[14],"is":[15],"a":[16,30,41,74,137],"result":[17],"of":[18,120],"cascaded":[19],"modules":[20],"whose":[21],"inference":[22],"delays":[23],"accumulate.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"transducer-based":[31],"speech":[32,38,66,75],"model":[34,85,95],"that":[35,103],"outputs":[36],"discrete":[37],"tokens":[39,67,90],"in":[40,118],"low-latency":[42],"streaming":[43,116],"fashion.":[44],"This":[45],"approach":[46],"eliminates":[47],"need":[49],"for":[50,115,128],"generating":[51],"text":[52],"output":[53],"first,":[54],"followed":[55],"by":[56,80],"machine":[57],"(MT)":[59],"text-to-speech":[61],"(TTS)":[62],"systems.":[63],"The":[64],"produced":[65],"can":[68],"be":[69],"directly":[70],"used":[71],"to":[72,87,96],"generate":[73],"signal":[76],"with":[77],"low":[78],"latency":[79],"utilizing":[81],"an":[82,92],"acoustic":[83,89],"language":[84,130],"(LM)":[86],"obtain":[88],"audio":[93],"codec":[94],"retrieve":[97],"waveform.":[99],"Experimental":[100],"results":[101,114],"show":[102],"proposed":[105],"method":[106],"outperforms":[107],"other":[108],"existing":[109],"approaches":[110],"achieves":[112],"state-of-the-art":[113],"terms":[119],"BLEU,":[121],"average":[122],"BLASER":[125],"2.0":[126],"scores":[127],"multiple":[129],"pairs":[131],"using":[132],"CVSS-C":[134],"dataset":[135],"as":[136],"benchmark.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}