{"id":"https://openalex.org/W4385764125","doi":"https://doi.org/10.24963/ijcai.2023/761","title":"Recent Advances in Direct Speech-to-text Translation","display_name":"Recent Advances in Direct Speech-to-text Translation","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764125","doi":"https://doi.org/10.24963/ijcai.2023/761"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/761","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/761","pdf_url":"https://www.ijcai.org/proceedings/2023/0761.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0761.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"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":"Chen Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"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/A5100624650","display_name":"Rong Ye","orcid":"https://orcid.org/0000-0003-2529-7755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Ye","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"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/A5017907143","display_name":"Chengqi Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengqi Zhao","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693713","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0008-3376-6762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","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":["NiuTrans Research, Shenyang, China","School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China; School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"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"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China; School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","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":["NiuTrans Research, Shenyang, China","School of Computer Science and Engineering, Northeastern University, Shenyang, China","NiuTrans Research, Shenyang, China; School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"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"]},{"raw_affiliation_string":"NiuTrans Research, Shenyang, China; School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6796","last_page":"6804"},"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8082883358001709},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5350476503372192},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5177997350692749},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48647329211235046},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4662334620952606},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.4278939366340637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42627355456352234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3622865676879883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3574855923652649},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10066685080528259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082883358001709},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5350476503372192},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5177997350692749},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48647329211235046},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4662334620952606},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4278939366340637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42627355456352234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3622865676879883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3574855923652649},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10066685080528259},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/761","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/761","pdf_url":"https://www.ijcai.org/proceedings/2023/0761.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/761","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/761","pdf_url":"https://www.ijcai.org/proceedings/2023/0761.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764125.pdf"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1556750318","https://openalex.org/W2582956876","https://openalex.org/W2788575190","https://openalex.org/W2899716505","https://openalex.org/W2936774411","https://openalex.org/W2936848022","https://openalex.org/W2936969148","https://openalex.org/W2949328740","https://openalex.org/W2964161387","https://openalex.org/W2972448360","https://openalex.org/W2973048981","https://openalex.org/W2973049979","https://openalex.org/W2989819126","https://openalex.org/W2998386507","https://openalex.org/W3025165719","https://openalex.org/W3033722096","https://openalex.org/W3034571331","https://openalex.org/W3034625919","https://openalex.org/W3035070478","https://openalex.org/W3036867795","https://openalex.org/W3093933225","https://openalex.org/W3096490862","https://openalex.org/W3097301532","https://openalex.org/W3097777922","https://openalex.org/W3097787369","https://openalex.org/W3112092703","https://openalex.org/W3113908264","https://openalex.org/W3152984045","https://openalex.org/W3153287399","https://openalex.org/W3161031484","https://openalex.org/W3162037819","https://openalex.org/W3162471442","https://openalex.org/W3163239510","https://openalex.org/W3163676755","https://openalex.org/W3164428426","https://openalex.org/W3168212167","https://openalex.org/W3169320628","https://openalex.org/W3172698324","https://openalex.org/W3173767661","https://openalex.org/W3176382501","https://openalex.org/W3176455679","https://openalex.org/W3176711365","https://openalex.org/W3177132412","https://openalex.org/W3177397495","https://openalex.org/W3196833881","https://openalex.org/W3205644108","https://openalex.org/W3209059054","https://openalex.org/W3213993043","https://openalex.org/W4221155340","https://openalex.org/W4221162032","https://openalex.org/W4221163209","https://openalex.org/W4221166780","https://openalex.org/W4223555773","https://openalex.org/W4223622550","https://openalex.org/W4224325263","https://openalex.org/W4226054021","https://openalex.org/W4285158365","https://openalex.org/W4285242522","https://openalex.org/W4285273653","https://openalex.org/W4287213456","https://openalex.org/W4287890956","https://openalex.org/W4288021071","https://openalex.org/W4297841689","https://openalex.org/W4302306287","https://openalex.org/W4308349017","https://openalex.org/W4312052802","https://openalex.org/W4320194748","https://openalex.org/W4372270126","https://openalex.org/W4385245566","https://openalex.org/W4385822287","https://openalex.org/W6776312876","https://openalex.org/W6803771590","https://openalex.org/W6809989930","https://openalex.org/W6863631769","https://openalex.org/W6863994431","https://openalex.org/W6864014924","https://openalex.org/W6925395861"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"Recently,":[0],"speech-to-text":[1],"translation":[2,26],"has":[3],"attracted":[4],"more":[5,7],"and":[6,9,54,73,76,99,104,117],"attention":[8],"many":[10,89],"studies":[11],"have":[12,67],"emerged":[13],"rapidly.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,35,120],"present":[19],"a":[20],"comprehensive":[21],"survey":[22],"on":[23,45],"direct":[24],"speech":[25],"aiming":[27],"to":[28,88],"summarize":[29,105],"the":[30,37,46,59,74,80,106],"current":[31],"state-of-the-art":[32],"techniques.":[33],"First,":[34],"categorize":[36],"existing":[38],"research":[39],"work":[40,86],"into":[41],"three":[42],"directions":[43,124],"based":[44],"main":[47,65],"challenges":[48],"---":[49],"modeling":[50,62],"burden,":[51,63],"data":[52,83,94],"scarcity,":[53,84],"application":[55,107],"issues.":[56],"To":[57],"tackle":[58],"problem":[60],"of":[61,82],"two":[64],"structures":[66],"been":[68],"proposed,":[69],"encoder-decoder":[70],"framework":[71],"(Transformer":[72],"variants)":[75],"multitask":[77],"frameworks.":[78],"For":[79],"challenge":[81],"recent":[85],"resorts":[87],"sophisticated":[90],"techniques,":[91],"such":[92],"as":[93],"augmentation,":[95],"pre-training,":[96],"knowledge":[97],"distillation,":[98],"multilingual":[100],"modeling.":[101],"We":[102],"analyze":[103],"issues,":[108],"which":[109],"include":[110],"real-time,":[111],"segmentation,":[112],"named":[113],"entity,":[114],"gender":[115],"bias,":[116],"code-switching.":[118],"Finally,":[119],"discuss":[121],"some":[122],"promising":[123],"for":[125],"future":[126],"work.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}