{"id":"https://openalex.org/W2124219499","doi":"https://doi.org/10.21437/eurospeech.2003-146","title":"Coupling vs. unifying: modeling techniques for speech-to-speech translation","display_name":"Coupling vs. unifying: modeling techniques for speech-to-speech translation","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2124219499","doi":"https://doi.org/10.21437/eurospeech.2003-146","mag":"2124219499"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-146","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5074146436","display_name":"Yuqing Gao","orcid":"https://orcid.org/0000-0001-8709-8378"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuqing Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5074146436"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"365","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.8441375494003296},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6379004716873169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6098377704620361},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5564430952072144},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49045416712760925},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4834531247615814},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4693613648414612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4558585286140442},{"id":"https://openalex.org/keywords/coupling","display_name":"Coupling (piping)","score":0.42170462012290955},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37433764338493347},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2726098299026489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441375494003296},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6379004716873169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6098377704620361},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5564430952072144},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49045416712760925},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4834531247615814},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4693613648414612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4558585286140442},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.42170462012290955},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37433764338493347},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2726098299026489},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-146","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"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":8,"referenced_works":["https://openalex.org/W1934019294","https://openalex.org/W1966812932","https://openalex.org/W2096175520","https://openalex.org/W2127718001","https://openalex.org/W2140968597","https://openalex.org/W2158333293","https://openalex.org/W2160842254","https://openalex.org/W2166986207"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W4386590854","https://openalex.org/W2163537793","https://openalex.org/W2251328660","https://openalex.org/W2162999097","https://openalex.org/W4237743574","https://openalex.org/W307032977","https://openalex.org/W4386794561","https://openalex.org/W4239803647","https://openalex.org/W2916997151"],"abstract_inverted_index":{"As":[0],"a":[1,8,49],"part":[2],"of":[3,41,52],"our":[4],"effort":[5],"to":[6,74],"develop":[7],"unified":[9],"computational":[10],"framework":[11],"for":[12,29],"speech-to-speech":[13],"translation,":[14],"so":[15],"that":[16],"sub-optimizations":[17],"or":[18,64],"local":[19],"optimizations":[20],"can":[21,71],"be":[22,72],"avoided,":[23],"we":[24,81],"are":[25,88],"developing":[26],"direct":[27,33],"models":[28],"speech":[30],"recognition.":[31,92],"In":[32,78],"model,":[34],"the":[35,39,75],"focus":[36],"is":[37],"on":[38],"creation":[40],"one":[42],"single":[43],"integrated":[44],"model":[45],",r":[46],"ather":[47],"than":[48],"complex":[50],"series":[51],"artifices,":[53],"therefore":[54],"various":[55],"factors":[56],"such":[57],"as":[58],"linguistics":[59],"and":[60,85],"language":[61],"features,":[62],"speaker":[63],"speaking":[65],"rate":[66],"differences,":[67],"different":[68],"acoustic":[69],"conditions,":[70],"applied":[73],"joint":[76],"optimization.":[77],"this":[79],"paper":[80],"discuss":[82],"how":[83],"linguistic":[84],"semantic":[86],"constraints":[87],"used":[89],"in":[90],"phoneme":[91]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}