{"id":"https://openalex.org/W4385823294","doi":"https://doi.org/10.21437/interspeech.2023-361","title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","display_name":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823294","doi":"https://doi.org/10.21437/interspeech.2023-361"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5071403524","display_name":"H. K. Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbyul Kim","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080739125","display_name":"Seunghyun Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghyun Seo","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065076995","display_name":"Lukas Jyuhn\u2010Hsiarn Lee","orcid":"https://orcid.org/0000-0003-1095-6877"},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lukas Lee","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111024465","display_name":"Seolki Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seolki Baek","raw_affiliation_strings":["NAVER Cloud, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud, South Korea","institution_ids":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58421416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1653","last_page":"1657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9945999979972839,"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/punctuation","display_name":"Punctuation","score":0.9528799653053284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.824518084526062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6696867942810059},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.625720202922821},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5508313179016113},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5388481616973877},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5007913112640381},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5005772113800049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4912261366844177},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4887826144695282},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47812286019325256},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2512010931968689}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9528799653053284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824518084526062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6696867942810059},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.625720202922821},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5508313179016113},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5388481616973877},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5007913112640381},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5005772113800049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4912261366844177},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4887826144695282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47812286019325256},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2512010931968689},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1587490638","https://openalex.org/W2119615570","https://openalex.org/W2397424575","https://openalex.org/W2512608784","https://openalex.org/W2513522215","https://openalex.org/W2766219058","https://openalex.org/W2802023636","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2913718171","https://openalex.org/W2933138175","https://openalex.org/W2963250244","https://openalex.org/W2973229104","https://openalex.org/W3007073761","https://openalex.org/W3015457435","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3018242354","https://openalex.org/W3036601975","https://openalex.org/W3081291520","https://openalex.org/W3094965760","https://openalex.org/W3096123040","https://openalex.org/W3096396467","https://openalex.org/W3096888553","https://openalex.org/W3125815078","https://openalex.org/W4224457787","https://openalex.org/W4296070361","https://openalex.org/W4309449460","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745","https://openalex.org/W2114358883"],"abstract_inverted_index":{"Punctuated":[0],"text":[1,47],"prediction":[2,106],"is":[3,29],"crucial":[4],"for":[5,44],"automatic":[6],"speech":[7,50],"recognition":[8],"as":[9],"it":[10],"enhances":[11],"readability":[12],"and":[13,73,95,107],"impacts":[14],"downstream":[15],"natural":[16],"language":[17],"processing":[18],"tasks.In":[19],"streaming":[20],"scenarios,":[21],"the":[22,71,82,93,100],"ability":[23],"to":[24,81],"predict":[25],"punctuation":[26,78,105],"in":[27],"real-time":[28],"particularly":[30],"desirable":[31],"but":[32],"presents":[33],"a":[34,42,52],"difficult":[35],"technical":[36],"challenge.In":[37],"this":[38],"work,":[39],"we":[40,97],"propose":[41],"method":[43],"predicting":[45],"punctuated":[46],"from":[48],"input":[49,72],"using":[51],"chunk-based":[53],"Transformer":[54],"encoder":[55],"trained":[56,65],"with":[57,66],"Connectionist":[58],"Temporal":[59],"Classification":[60],"(CTC)":[61],"loss.The":[62],"acoustic":[63],"model":[64],"long":[67],"sequences":[68,75],"by":[69,88],"concatenating":[70],"target":[74],"can":[76],"learn":[77],"marks":[79],"attached":[80],"end":[83],"of":[84,104],"sentences":[85],"more":[86],"effectively.Additionally,":[87],"combining":[89],"CTC":[90],"losses":[91],"on":[92],"chunks":[94],"utterances,":[96],"achieved":[98],"both":[99],"improved":[101],"F1":[102],"score":[103],"Word":[108],"Error":[109],"Rate":[110],"(WER).":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-08-15T00:00:00"}