{"id":"https://openalex.org/W2129336405","doi":null,"title":"Real-time Incremental Speech-to-Speech Translation of Dialogs","display_name":"Real-time Incremental Speech-to-Speech Translation of Dialogs","publication_year":2012,"publication_date":"2012-06-03","ids":{"openalex":"https://openalex.org/W2129336405","mag":"2129336405"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.9109","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.9109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/export/sites/att_labs/techdocs/TD_100755.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5111475783","display_name":"Srinivas Bangalore","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Bangalore","raw_affiliation_strings":["AT&T Laboratories---Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories---Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911746","display_name":"Vivek Kumar Rangarajan Sridhar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Kumar Rangarajan Sridhar","raw_affiliation_strings":["AT&T Laboratories---Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories---Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027939466","display_name":"Prakash Kolan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prakash Kolan","raw_affiliation_strings":["AT&T Laboratories---Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories---Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010570444","display_name":"Ladan Golipour","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ladan Golipour","raw_affiliation_strings":["AT&T Laboratories---Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories---Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009721583","display_name":"Aura Jimenez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aura Jimenez","raw_affiliation_strings":["AT&T Laboratories---Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories---Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":6.3843,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.96850614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"437","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9692000150680542,"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":0.9692000150680542,"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":0.024800000712275505,"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":0.00430000014603138,"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/speech-to-speech-translation","display_name":"speech-to-speech translation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/real-time-translation","display_name":"real-time translation","score":0.875},{"id":"https://openalex.org/keywords/session-initiation-protocol","display_name":"Session Initiation Protocol","score":0.9259999990463257},{"id":"https://openalex.org/keywords/telephone-communication","display_name":"telephone communication","score":0.5630000233650208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.953000009059906},{"id":"https://openalex.org/keywords/accuracy-latency-trade-off","display_name":"accuracy-latency trade-off","score":0.7310000061988831},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.7089999914169312}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.887026309967041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518469333648682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7114303112030029},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6606974601745605},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5377040505409241},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5027637481689453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4715174436569214},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4620347321033478},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4556964933872223},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.45268574357032776},{"id":"https://openalex.org/C41878487","wikidata":"https://www.wikidata.org/wiki/Q191018","display_name":"Session Initiation Protocol","level":3,"score":0.4253332018852234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189111590385437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40294402837753296},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.9109","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.9109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/export/sites/att_labs/techdocs/TD_100755.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.374.349","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.374.349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/N/N12/N12-1048.pdf","raw_type":"text"},{"id":"mag:2129336405","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/N12-1048.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420633","display_name":"North American Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"North American Chapter of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W90695545","https://openalex.org/W1526763309","https://openalex.org/W1538023239","https://openalex.org/W1625582487","https://openalex.org/W1631260214","https://openalex.org/W1650129375","https://openalex.org/W2033010331","https://openalex.org/W2070293423","https://openalex.org/W2075548498","https://openalex.org/W2099033952","https://openalex.org/W2101105183","https://openalex.org/W2120309221","https://openalex.org/W2124807415","https://openalex.org/W2135708429","https://openalex.org/W2149327368","https://openalex.org/W2156985047","https://openalex.org/W2165861304","https://openalex.org/W2170120894","https://openalex.org/W2291598608","https://openalex.org/W2394530649"],"related_works":["https://openalex.org/W2400940717","https://openalex.org/W4297841754","https://openalex.org/W199184951","https://openalex.org/W4206534379","https://openalex.org/W3198267530","https://openalex.org/W316025943","https://openalex.org/W1486199320","https://openalex.org/W4379471040","https://openalex.org/W7098161387","https://openalex.org/W55183045"],"abstract_inverted_index":{"In":[0,24],"a":[1,45,52],"conventional":[2],"telephone":[3],"conversation":[4],"between":[5,40],"two":[6,41],"speakers":[7,18],"of":[8,31,71],"the":[9,12,17,20,29,49,79,83,87,106,127,133],"same":[10],"language,":[11],"interaction":[13],"is":[14,65],"real-time":[15,54,92],"and":[16,86,104],"process":[19],"information":[21],"stream":[22],"incrementally.":[23],"this":[25,102],"work,":[26],"we":[27],"address":[28],"problem":[30,50],"incremental":[32,113,128],"speech-to-speech":[33],"translation":[34,64],"(S2S)":[35],"that":[36,119],"enables":[37],"cross-lingual":[38,94],"communication":[39],"remote":[42],"participants":[43],"over":[44],"telephone.":[46],"We":[47,77,96],"investigate":[48],"in":[51,101,108,112],"novel":[53],"Session":[55],"Initiation":[56],"Protocol":[57],"(SIP)":[58],"based":[59,68],"S2S":[60,84],"framework.":[61],"The":[62],"speech":[63,75,114],"performed":[66,100],"incrementally":[67],"on":[69],"generation":[70],"partial":[72],"hypotheses":[73],"from":[74],"recognition.":[76],"describe":[78],"statistical":[80],"models":[81],"comprising":[82],"system":[85],"SIP":[88],"architecture":[89],"for":[90],"enabling":[91],"two-way":[93],"dialog.":[95],"present":[97],"dialog":[98],"experiments":[99],"framework":[103],"study":[105],"tradeoff":[107],"accuracy":[109],"versus":[110],"latency":[111,134],"translation.":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"high":[120],"quality":[121],"translations":[122],"can":[123],"be":[124],"generated":[125],"with":[126,130,136],"approach":[129],"approximately":[131],"half":[132],"associated":[135],"nonincremental":[137],"approach.":[138],"1":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}