{"id":"https://openalex.org/W4416798471","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249353","title":"Semi-Supervised End-to-End Speech-to-Text Translation with Joint Text-to-Text and Speech-to-Text Decoding","display_name":"Semi-Supervised End-to-End Speech-to-Text Translation with Joint Text-to-Text and Speech-to-Text Decoding","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798471","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249353"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Orihashi","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027868267","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0001-5343-4660"},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102511251","display_name":"Taiga Yamane","orcid":null},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taiga Yamane","raw_affiliation_strings":["NTT, Inc.,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc.,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101463708"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20699467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"909","last_page":"914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9222000241279602,"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":0.9222000241279602,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05429999902844429,"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":0.006200000178068876,"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/decoding-methods","display_name":"Decoding methods","score":0.7437999844551086},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6269999742507935},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.6132000088691711},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5677000284194946},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.40869998931884766},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3887999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5853999853134155},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5677000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4318000078201294},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C107645828","wikidata":"https://www.wikidata.org/wiki/Q12070446","display_name":"System model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2605131327","https://openalex.org/W2936774411","https://openalex.org/W2963109507","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2964161387","https://openalex.org/W2964172053","https://openalex.org/W2972448360","https://openalex.org/W3006988520","https://openalex.org/W3008125272","https://openalex.org/W3008549139","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3092085609","https://openalex.org/W3096338464","https://openalex.org/W3096490862","https://openalex.org/W3173767661","https://openalex.org/W3174481817","https://openalex.org/W3197223534","https://openalex.org/W4280601369","https://openalex.org/W4300558631","https://openalex.org/W4385570101","https://openalex.org/W4385570493","https://openalex.org/W4392904172"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,20,49,54,63,140],"novel":[4],"semi-supervised":[5],"end-to-end":[6],"speech-to-text":[7],"translation":[8,22],"(S2TT)":[9],"approach":[10],"that":[11,129,137],"leverages":[12],"pseudo-labeling":[13],"(PL)":[14],"through":[15],"joint":[16],"decoding":[17],"with":[18,62,91],"both":[19,101],"text-totext":[21],"(T2TT)":[23],"model":[24,52,104,114,119],"and":[25,80,105],"an":[26],"S2TT":[27,51,81,103,118,143],"model.":[28,65,144],"While":[29],"pseudolabeling":[30],"has":[31],"proven":[32],"effective":[33],"in":[34,40],"mitigating":[35],"the":[36,102,106,112,117],"data":[37,72,87],"scarcity":[38],"issue":[39],"S2TT,":[41],"conventional":[42,134],"PL":[43,135],"approaches":[44],"typically":[45],"rely":[46],"either":[47],"on":[48,70,76,84,123],"standalone":[50],"or":[53,142],"cascade":[55,67,107],"system":[56,108],"combining":[57],"automatic":[58],"speech":[59],"recognition":[60],"(ASR)":[61],"T2TT":[64,113,141],"However,":[66],"systems":[68],"trained":[69],"out-of-domain":[71],"often":[73],"perform":[74],"poorly":[75],"target":[77],"domain":[78],"inputs,":[79],"models":[82],"fine-tuned":[83],"limited":[85],"in-domain":[86],"tend":[88],"to":[89,115],"struggle":[90],"low-occurrence":[92],"tokens.":[93,125],"To":[94],"address":[95],"these":[96],"limitations,":[97],"our":[98,130],"method":[99,132],"employs":[100],"for":[109],"PL,":[110],"using":[111],"complement":[116],"by":[120],"improving":[121],"accuracy":[122],"rare":[124],"Experimental":[126],"results":[127],"demonstrate":[128],"proposed":[131],"outperforms":[133],"strategies":[136],"utilize":[138],"only":[139]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}