{"id":"https://openalex.org/W4392904548","doi":"https://doi.org/10.1109/icassp48485.2024.10445849","title":"Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition","display_name":"Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904548","doi":"https://doi.org/10.1109/icassp48485.2024.10445849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100385729","display_name":"Chen Xu","orcid":"https://orcid.org/0000-0002-7238-7254"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Xu","raw_affiliation_strings":["Harbin Engineering University,College of Computer Science and Technology,Harbin,China","College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683620","display_name":"Xiaoqian Liu","orcid":"https://orcid.org/0009-0007-0440-7341"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqian Liu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China","School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108865467","display_name":"Erfeng He","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erfeng He","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China","School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349352","display_name":"Yuhao Zhang","orcid":"https://orcid.org/0000-0002-9856-436X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhang","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China","School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674914","display_name":"Qianqian Dong","orcid":"https://orcid.org/0009-0001-7001-7583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianqian Dong","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China","NiuTrans Research, Shenyang, China","School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370155","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0000-0002-6537-7007"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China","School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067145421","display_name":"Dapeng Man","orcid":"https://orcid.org/0000-0003-1177-3693"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Man","raw_affiliation_strings":["Harbin Engineering University,College of Computer Science and Technology,Harbin,China","College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101451232","display_name":"Yang Wu","orcid":"https://orcid.org/0000-0003-4156-0218"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Yang","raw_affiliation_strings":["Harbin Engineering University,College of Computer Science and Technology,Harbin,China","College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12176","last_page":"12180"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.8392343521118164},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7556686997413635},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.641115665435791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.569446325302124},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5537956357002258},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5073320269584656},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48751136660575867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4634537398815155},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.43418973684310913},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42213284969329834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.384337455034256},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1130477786064148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08546364307403564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392343521118164},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7556686997413635},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.641115665435791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.569446325302124},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5537956357002258},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5073320269584656},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48751136660575867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4634537398815155},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43418973684310913},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42213284969329834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.384337455034256},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1130477786064148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08546364307403564},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1161215003","display_name":"\u57fa\u4e8e\u5185\u5bb9\u7684\u65b0\u578b\u901a\u4fe1\u7f51\u7edc\u4e3b\u52a8\u9632\u5fa1\u57fa\u7840\u7406\u8bba\u548c\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61831007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2624032260","display_name":"\u57fa\u4e8e\u65e0\u7ebf\u7f51\u7edc\u7269\u7406\u5c42\u4fe1\u606f\u7684\u7ec6\u7c92\u5ea6\u52a8\u4f5c\u8bc6\u522b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61971154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3064853585","display_name":null,"funder_award_id":"U21B2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G627077469","display_name":null,"funder_award_id":"U2003206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6466369849","display_name":null,"funder_award_id":"62272127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G752701465","display_name":null,"funder_award_id":"U22A2036","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":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2582956876","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2949328740","https://openalex.org/W2963736842","https://openalex.org/W2964172053","https://openalex.org/W3007142233","https://openalex.org/W3037469336","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3196833881","https://openalex.org/W3197140813","https://openalex.org/W4221163209","https://openalex.org/W4287890956","https://openalex.org/W4385570154","https://openalex.org/W4385571004","https://openalex.org/W4385571120","https://openalex.org/W4385764125","https://openalex.org/W6769269733","https://openalex.org/W6795829636","https://openalex.org/W6846505686","https://openalex.org/W6849230176"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663","https://openalex.org/W4248308508"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,67],"present":[4],"synchronous":[5],"bilingual":[6],"Connectionist":[7],"Temporal":[8],"Classification":[9],"(CTC),":[10],"an":[11,69],"innovative":[12],"framework":[13],"that":[14,73],"leverages":[15],"dual":[16],"CTC":[17,65],"to":[18],"bridge":[19],"the":[20,28,45,61,79,98],"gaps":[21],"of":[22,100],"both":[23],"modality":[24],"and":[25,35,49,56,105],"language":[26],"in":[27,64,93],"speech":[29,94],"translation":[30,36],"(ST)":[31],"task.":[32],"Utilizing":[33],"transcript":[34],"as":[37,51,53],"concurrent":[38],"objectives":[39],"for":[40],"CTC,":[41],"our":[42,87],"model":[43],"bridges":[44],"gap":[46],"between":[47,54],"audio":[48],"text":[50],"well":[52],"source":[55,111],"target":[57],"languages.":[58],"Building":[59],"upon":[60],"recent":[62],"advances":[63],"application,":[66],"develop":[68],"enhanced":[70],"variant,":[71],"BiL-CTC+,":[72],"establishes":[74],"new":[75],"state-of-the-art":[76],"performances":[77],"on":[78,103],"MuST-C":[80],"ST":[81],"benchmarks":[82],"under":[83],"resource-constrained":[84],"scenarios.":[85],"Intriguingly,":[86],"method":[88],"also":[89],"yields":[90],"significant":[91],"improvements":[92],"recognition":[95],"performance,":[96],"revealing":[97],"effect":[99],"cross-lingual":[101],"learning":[102],"transcription":[104],"demonstrating":[106],"its":[107],"broad":[108],"applicability.":[109],"The":[110],"code":[112],"is":[113],"available":[114],"at":[115],"https://github.com/xuchennlp/S2T.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}