{"id":"https://openalex.org/W7137971434","doi":"https://doi.org/10.1609/aaai.v40i38.40449","title":"PLaST: Towards Paralinguistic-aware Speech Translation","display_name":"PLaST: Towards Paralinguistic-aware Speech Translation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137971434","doi":"https://doi.org/10.1609/aaai.v40i38.40449"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i38.40449","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40449","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40449/44410","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40449/44410","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129711302","display_name":"Yi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Li","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652264","display_name":"Rui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009549585","display_name":"R. Zhang","orcid":"https://orcid.org/0000-0001-7892-7090"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiquan Zhang","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722019","display_name":"Jinsong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724217","display_name":"Daimeng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":["Huawei Technologies Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749043","display_name":"Min Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Technologies Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129689397","display_name":"Yidong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":["Xiamen University"],"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129711302"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18433671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"31805","last_page":"31813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7360000014305115,"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":0.7360000014305115,"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":0.09969999641180038,"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":0.040300000458955765,"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/paralanguage","display_name":"Paralanguage","score":0.9962000250816345},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.474700003862381},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.3799999952316284},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.30250000953674316}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9962000250816345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650999784469604},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5690000057220459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.474700003862381},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i38.40449","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40449","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40449/44410","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40449","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40449","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40449/44410","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6365131139755249}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G179328913","display_name":null,"funder_award_id":"62476232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5610393340","display_name":null,"funder_award_id":"62036004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8497982794","display_name":null,"funder_award_id":"6203600","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137971434.pdf","grobid_xml":"https://content.openalex.org/works/W7137971434.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0,77],"translation":[1,70,166,203],"(ST)":[2],"aims":[3],"to":[4,59,68,103,158,211],"translate":[5],"speech":[6,18,65,97,202],"from":[7,133],"a":[8,35,80,96,100,113,122],"source":[9],"language":[10],"into":[11],"text":[12,120],"in":[13,194],"the":[14,32,90,119,130,138,152,170,186,200],"target":[15],"language.":[16],"Naturally,":[17],"signals":[19],"contain":[20],"paralinguistic":[21,53,61,87,108,139,195],"cues":[22,62,88],"beyond":[23,89],"linguistic":[24,91,106,115,153],"content,":[25],"which":[26,55,84],"could":[27],"influence":[28],"or":[29],"even":[30],"alter":[31],"interpretation":[33],"of":[34,52,176],"lexically":[36],"identical":[37],"sentence,":[38],"thereby":[39],"yielding":[40],"distinct":[41],"translations.":[42],"However,":[43],"existing":[44],"ST":[45,213],"models":[46],"lack":[47],"direct":[48],"and":[49,63,99,107,143,165,179],"sufficient":[50],"modeling":[51],"information,":[54],"limits":[56],"their":[57],"ability":[58],"perceive":[60],"understand":[64],"comprehensively,":[66],"leading":[67],"degraded":[69],"performance.":[71],"In":[72],"response,":[73],"we":[74],"propose":[75],"Paralinguistic-aware":[76],"Translation":[78],"(PLaST),":[79],"novel":[81],"dual-branch":[82],"framework":[83],"directly":[85],"leverages":[86],"content.":[92],"Specifically,":[93],"PLaST":[94,168,208],"employs":[95],"encoder":[98],"style":[101],"extractor":[102],"independently":[104],"generate":[105],"representations,":[109],"respectively.":[110],"To":[111],"obtain":[112],"purified":[114],"representation":[116,154],"aligned":[117],"with":[118,145,151,173],"representation,":[121],"hierarchical":[123],"Optimal":[124],"Transport":[125],"(OT)":[126],"is":[127,141],"applied":[128],"on":[129,185,199],"layer-wise":[131],"outputs":[132],"an":[134,146,174],"LLM":[135],"decoder.":[136],"Then,":[137],"information":[140],"retrieved":[142],"refined":[144],"Attention-based":[147],"Retrieval":[148],"(AR)":[149],"module,":[150],"serving":[155],"as":[156],"queries":[157],"enable":[159],"joint":[160],"guidance":[161],"for":[162],"semantic":[163],"understanding":[164],"generation.":[167],"outperforms":[169],"strong":[171],"baseline":[172],"average":[175],"5.0":[177],"directional":[178],"4.5":[180],"global":[181],"contrastive":[182],"likelihood":[183],"scores":[184],"paralinguistic-sensitive":[187],"benchmark":[188,204],"ContraProST,":[189],"demonstrating":[190],"its":[191],"superior":[192],"capability":[193],"perception.":[196],"Further":[197],"experiments":[198],"standard":[201],"CoVoST-2":[205],"show":[206],"that":[207],"generalizes":[209],"well":[210],"typical":[212],"scenarios.":[214]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}
