{"id":"https://openalex.org/W4378651270","doi":"https://doi.org/10.4995/thesis/10251/193680","title":"Transformer Models for Machine Translation and Streaming Automatic Speech Recognition","display_name":"Transformer Models for Machine Translation and Streaming Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-04-25","ids":{"openalex":"https://openalex.org/W4378651270","doi":"https://doi.org/10.4995/thesis/10251/193680"},"language":"en","primary_location":{"id":"doi:10.4995/thesis/10251/193680","is_oa":true,"landing_page_url":"http://dx.doi.org/10.4995/thesis/10251/193680","pdf_url":"https://riunet.upv.es/bitstreams/45544024-282d-4140-973a-826e43eb25fb/download","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://riunet.upv.es/bitstreams/45544024-282d-4140-973a-826e43eb25fb/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033477251","display_name":"Pau Baquero Arnal","orcid":null},"institutions":[{"id":"https://openalex.org/I1318003438","display_name":"RELX Group (Netherlands)","ror":"https://ror.org/02scfj030","country_code":"NL","type":"company","lineage":["https://openalex.org/I1318003438","https://openalex.org/I4210160603"]},{"id":"https://openalex.org/I4210094921","display_name":"German Police University","ror":"https://ror.org/01h7vw195","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210094921"]},{"id":"https://openalex.org/I4210096575","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/00aejfc65","country_code":"PY","type":"government","lineage":["https://openalex.org/I4210096575"]},{"id":"https://openalex.org/I4210137169","display_name":"La Universidad Americana","ror":"https://ror.org/038e47q18","country_code":"NI","type":"education","lineage":["https://openalex.org/I4210137169"]},{"id":"https://openalex.org/I4210142311","display_name":"Excelia Business School","ror":"https://ror.org/051gb6s93","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142311"]}],"countries":["DE","FR","NI","NL","PY"],"is_corresponding":true,"raw_author_name":"Pau Baquero Arnal","raw_affiliation_strings":["de traducci\u00f3n de noticias o el de subtitulaci\u00f3n autom\u00e1tica de televisi\u00f3n. El ASR y MT tambi\u00e9n se pueden com-binar entre s\u00ed,","la meua parella Clara,","Jorge Civera i Albert Sanchis. A","m\u00e9s de ser excel\u2022lents en la seua forma de treballar, tamb\u00e9 destaquen per les seues qualitats humanes","contiene, en la meduda que ayudan a mejorar el rendimiento de los sistemas autom\u00e1ticos de los que dependen. Esta tesis contiene una aplicaci\u00f3n de la arquitectura Transformer al MT tal y como fue concebida, mediante la que obtenemos resultados de primer nivel en traducci\u00f3n de lenguas semejantes. En cap\u00edtulos subsecuentes,","de banda al meu director de tesi Alfons Juan","la meua germana Marina,","part de la meua vida que segur que em marcar\u00e0 de cara al futur","tesis aborda la adaptaci\u00f3n del Transformer como modelo de lenguaje para sistemas h\u00edbri-dos de ASR en vivo. Posteriormente, describe la aplicaci\u00f3n de este tipus de sistemas al caso de uso de subtitulaci\u00f3n de televisi\u00f3n, participando en una com-petici\u00f3n p\u00fablica de RTVE donde obtenemos la primera posici\u00f3n con un marge importante. Tambi\u00e9n demostramos que la mejora se debe principalmenta a la tecnolog\u00eda desarrollada y no tanto a la parte de los datos. xi","meua etapa predoctoral en el grup de recerca MLLP he tingut la sort de compartir viatge amb un equip de persones que,"],"affiliations":[{"raw_affiliation_string":"de traducci\u00f3n de noticias o el de subtitulaci\u00f3n autom\u00e1tica de televisi\u00f3n. El ASR y MT tambi\u00e9n se pueden com-binar entre s\u00ed,","institution_ids":["https://openalex.org/I1318003438"]},{"raw_affiliation_string":"la meua parella Clara,","institution_ids":["https://openalex.org/I4210137169"]},{"raw_affiliation_string":"Jorge Civera i Albert Sanchis. A","institution_ids":[]},{"raw_affiliation_string":"m\u00e9s de ser excel\u2022lents en la seua forma de treballar, tamb\u00e9 destaquen per les seues qualitats humanes","institution_ids":["https://openalex.org/I4210142311"]},{"raw_affiliation_string":"contiene, en la meduda que ayudan a mejorar el rendimiento de los sistemas autom\u00e1ticos de los que dependen. Esta tesis contiene una aplicaci\u00f3n de la arquitectura Transformer al MT tal y como fue concebida, mediante la que obtenemos resultados de primer nivel en traducci\u00f3n de lenguas semejantes. En cap\u00edtulos subsecuentes,","institution_ids":[]},{"raw_affiliation_string":"de banda al meu director de tesi Alfons Juan","institution_ids":[]},{"raw_affiliation_string":"la meua germana Marina,","institution_ids":["https://openalex.org/I4210094921"]},{"raw_affiliation_string":"part de la meua vida que segur que em marcar\u00e0 de cara al futur","institution_ids":[]},{"raw_affiliation_string":"tesis aborda la adaptaci\u00f3n del Transformer como modelo de lenguaje para sistemas h\u00edbri-dos de ASR en vivo. Posteriormente, describe la aplicaci\u00f3n de este tipus de sistemas al caso de uso de subtitulaci\u00f3n de televisi\u00f3n, participando en una com-petici\u00f3n p\u00fablica de RTVE donde obtenemos la primera posici\u00f3n con un marge importante. Tambi\u00e9n demostramos que la mejora se debe principalmenta a la tecnolog\u00eda desarrollada y no tanto a la parte de los datos. xi","institution_ids":["https://openalex.org/I4210096575"]},{"raw_affiliation_string":"meua etapa predoctoral en el grup de recerca MLLP he tingut la sort de compartir viatge amb un equip de persones que,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033477251"],"corresponding_institution_ids":["https://openalex.org/I1318003438","https://openalex.org/I4210094921","https://openalex.org/I4210096575","https://openalex.org/I4210137169","https://openalex.org/I4210142311"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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/transformer","display_name":"Transformer","score":0.6365271806716919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6188434362411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5936925411224365},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45334669947624207},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.427243173122406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36705800890922546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3443366587162018},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22917413711547852},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12756195664405823},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.047755420207977295}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6365271806716919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6188434362411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5936925411224365},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45334669947624207},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.427243173122406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36705800890922546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3443366587162018},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22917413711547852},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12756195664405823},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.047755420207977295},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4995/thesis/10251/193680","is_oa":true,"landing_page_url":"http://dx.doi.org/10.4995/thesis/10251/193680","pdf_url":"https://riunet.upv.es/bitstreams/45544024-282d-4140-973a-826e43eb25fb/download","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","raw_type":"dissertation"},{"id":"pmh:oai:riunet.upv.es:10251/193680","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/193680","pdf_url":"https://riunet.upv.es/bitstream/10251/193680/4/Baquero%20-%20Transformer%20models%20for%20Machine%20Translation%20and%20Streaming%20Automatic%20Speech%20Recognition.pdf","source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"}],"best_oa_location":{"id":"doi:10.4995/thesis/10251/193680","is_oa":true,"landing_page_url":"http://dx.doi.org/10.4995/thesis/10251/193680","pdf_url":"https://riunet.upv.es/bitstreams/45544024-282d-4140-973a-826e43eb25fb/download","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","raw_type":"dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378651270.pdf"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W126222424","https://openalex.org/W280003846","https://openalex.org/W1494108583","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W1816313093","https://openalex.org/W1848260265","https://openalex.org/W1977286842","https://openalex.org/W1994536225","https://openalex.org/W1995929454","https://openalex.org/W2008554732","https://openalex.org/W2064675550","https://openalex.org/W2091981305","https://openalex.org/W2095705004","https://openalex.org/W2100649405","https://openalex.org/W2106279089","https://openalex.org/W2120861206","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2138889249","https://openalex.org/W2146502635","https://openalex.org/W2149327368","https://openalex.org/W2158069733","https://openalex.org/W2183341477","https://openalex.org/W2251321385","https://openalex.org/W2284660317","https://openalex.org/W2288502450","https://openalex.org/W2401969231","https://openalex.org/W2471933213","https://openalex.org/W2512608784","https://openalex.org/W2518037268","https://openalex.org/W2566125645","https://openalex.org/W2595715041","https://openalex.org/W2760656271","https://openalex.org/W2763120645","https://openalex.org/W2886845974","https://openalex.org/W2891143126","https://openalex.org/W2896457183","https://openalex.org/W2897105542","https://openalex.org/W2898625294","https://openalex.org/W2900707131","https://openalex.org/W2902363747","https://openalex.org/W2903193068","https://openalex.org/W2903399267","https://openalex.org/W2912815991","https://openalex.org/W2917324689","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2962784628","https://openalex.org/W2962965465","https://openalex.org/W2963216553","https://openalex.org/W2963443683","https://openalex.org/W2963971085","https://openalex.org/W2963979492","https://openalex.org/W2964050280","https://openalex.org/W2964199361","https://openalex.org/W2970152385","https://openalex.org/W2972528057","https://openalex.org/W2981857663","https://openalex.org/W2982666195","https://openalex.org/W2998814410","https://openalex.org/W3002961036","https://openalex.org/W3004728855","https://openalex.org/W3008191852","https://openalex.org/W3015457435","https://openalex.org/W3015926140","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3025165719","https://openalex.org/W3027687786","https://openalex.org/W3030163527","https://openalex.org/W3035207248","https://openalex.org/W3093620947","https://openalex.org/W3097777922","https://openalex.org/W3097973766","https://openalex.org/W3101096852","https://openalex.org/W3101732184","https://openalex.org/W3125815078","https://openalex.org/W3127273935","https://openalex.org/W3133499175","https://openalex.org/W3134113591","https://openalex.org/W3148654612","https://openalex.org/W3160054295","https://openalex.org/W3161873870","https://openalex.org/W3198641750","https://openalex.org/W3210615406","https://openalex.org/W4224137820","https://openalex.org/W4225665589","https://openalex.org/W4284881636","https://openalex.org/W4285091908","https://openalex.org/W4285140158","https://openalex.org/W4292779060","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2775554247","https://openalex.org/W2903810591","https://openalex.org/W2883671469","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W2728761353","https://openalex.org/W2949454572"],"abstract_inverted_index":{"[ES]":[0],"El":[1,87,129],"procesamiento":[2],"del":[3,55,160,170,236],"lenguaje":[4,241],"natural":[5],"(NLP)":[6],"es":[7],"un":[8,101,281],"conjunto":[9],"de":[10,15,27,78,84,97,107,118,120,124,127,148,151,156,172,191,195,204,220,225,240,246,254,257,261,263,265,273,302],"problemas":[11,42,115],"computacionales":[12],"con":[13,20,145,280],"aplicaciones":[14,167],"m\u00e1xima":[16],"relevancia,":[17],"que":[18,30,70,180,185,197,217,286],"junto":[19],"otras":[21,146],"tecnolog\u00edas":[22],"inform\u00e1ticas":[23],"se":[24,38,134,289],"ha":[25,31],"beneficiado":[26],"la":[28,47,183,205,216,234,252,277,287,293,300],"revoluci\u00f3n":[29],"significado":[32],"el":[33,45,52,68,117,123,189],"aprendizaje":[34],"profundo.":[35],"Esta":[36,199],"tesis":[37,113,174,200,232],"centra":[39],"en":[40,63,72,82,182,223,248,268],"dos":[41,245],"fundamentales":[43],"para":[44,74,93,104,153,162,242],"NLP:":[46,149],"traducci\u00f3n":[48,119,224],"autom\u00e1tica":[49,59,126],"(MT)":[50],"y":[51,80,89,131,211,296],"reconocimiento":[53],"autom\u00e1tico":[54],"habla":[56,161],"o":[57,122,144,158],"transcripci\u00f3n":[58],"(ASR);":[60],"as\u00ed":[61],"como":[62,116,212,238],"una":[64,105,202,269],"arquitectura":[65,206],"neuronal":[66],"profunda,":[67],"Transformer,":[69],"pondremos":[71],"pr\u00e1ctica":[73],"mejorar":[75,188],"las":[76,178],"soluciones":[77,147],"MT":[79,90,132,209],"ASR":[81,88,130,247],"algunas":[83],"sus":[85],"aplicaciones.":[86],"pueden":[91,135,176],"servir":[92],"obtener":[94],"textos":[95,152],"multiling\u00fces":[96],"alta":[98],"calidad":[99],"a":[100,187,292,299],"coste":[102],"razonable":[103],"diversidad":[106],"contenidos":[108],"audiovisuales.":[109],"Concre-":[110],"tamente,":[111],"esta":[112,173,231],"aborda":[114,233],"noticias":[121],"subtitulaci\u00f3n":[125,264],"televisi\u00f3n.":[128],"tambi\u00e9n":[133],"com-":[136,270],"binar":[137],"entre":[138],"s\u00ed,":[139],"generando":[140],"autom\u00e1ticamente":[141],"subt\u00edtulos":[142],"traducidos,":[143],"resumen":[150],"producir":[154],"res\u00famenes":[155],"discursos,":[157],"s\u00edntesis":[159],"crear":[163],"doblajes":[164],"autom\u00e1ticos.":[165],"Estas":[166],"quedan":[168],"fuera":[169],"alcance":[171],"pero":[175],"aprovechar":[177],"contribuciones":[179],"contiene,":[181],"meduda":[184],"ayudan":[186],"rendimiento":[190],"los":[192,196,303],"sistemas":[193,243,258],"autom\u00e1ticos":[194],"dependen.":[198],"contiene":[201],"aplicaci\u00f3n":[203,253],"Transformer":[207,237],"al":[208,259],"tal":[210],"fue":[213],"concebida,":[214],"mediante":[215],"obtenemos":[218,276],"resultados":[219],"primer":[221],"nivel":[222],"lenguas":[226],"semejantes.":[227],"En":[228],"cap\u00edtulos":[229],"subsecuentes,":[230],"adaptaci\u00f3n":[235],"modelo":[239],"h\u00edbri-":[244],"vivo.":[249],"Posteriormente,":[250],"describe":[251],"este":[255],"tipus":[256],"caso":[260],"uso":[262],"televisi\u00f3n,":[266],"participando":[267],"petici\u00f3n":[271],"p\u00fablica":[272],"RTVE":[274],"donde":[275],"primera":[278],"posici\u00f3n":[279],"marge":[282],"importante.":[283],"Tambi\u00e9n":[284],"demostramos":[285],"mejora":[288],"debe":[290],"principalmenta":[291],"tecnolog\u00eda":[294],"desarrollada":[295],"no":[297],"tanto":[298],"parte":[301],"datos.":[304]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2023-05-30T00:00:00"}