{"id":"https://openalex.org/W4406461754","doi":"https://doi.org/10.1109/slt61566.2024.10832175","title":"Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation","display_name":"Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461754","doi":"https://doi.org/10.1109/slt61566.2024.10832175"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104107801","display_name":"Travis Bartley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis Bartley","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409299","display_name":"Xu H","orcid":"https://orcid.org/0009-0001-1201-443X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleksii Hrinchuk","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033043101","display_name":"Georg Kucsko","orcid":"https://orcid.org/0000-0002-4189-3154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Kucsko","raw_affiliation_strings":["Suno Inc,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Suno Inc,Cambridge,MA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5040007143"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.0336,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8227529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"262"},"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/sequence","display_name":"Sequence (biology)","score":0.6426628828048706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6362025737762451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6014895439147949},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5593210458755493},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5560949444770813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4923754930496216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3813937306404114},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09627768397331238},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08272114396095276}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6426628828048706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362025737762451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6014895439147949},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5593210458755493},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5560949444770813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4923754930496216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813937306404114},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09627768397331238},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08272114396095276},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2799473636","https://openalex.org/W2896457183","https://openalex.org/W2962989741","https://openalex.org/W2963979492","https://openalex.org/W2998572311","https://openalex.org/W3030437843","https://openalex.org/W3093579165","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3119308075","https://openalex.org/W3143186397","https://openalex.org/W3197674197","https://openalex.org/W3198587774","https://openalex.org/W3198694222","https://openalex.org/W4221146809","https://openalex.org/W4226272674","https://openalex.org/W4311000453","https://openalex.org/W4366197103","https://openalex.org/W4385245566","https://openalex.org/W4386566728","https://openalex.org/W4391021542","https://openalex.org/W4391021797","https://openalex.org/W4392271354","https://openalex.org/W4392903765","https://openalex.org/W4392909067","https://openalex.org/W4399447692","https://openalex.org/W6633847657","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6771467084","https://openalex.org/W6784614252","https://openalex.org/W6846002384","https://openalex.org/W6847363464","https://openalex.org/W6851766456","https://openalex.org/W6856547296","https://openalex.org/W6856928200","https://openalex.org/W6862096054","https://openalex.org/W6869410597"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,113],"new":[4],"method":[5,105],"for":[6,10],"training":[7,22,39,62,79,92,128,148],"sequence-to-sequence":[8],"models":[9,23,66],"speech":[11,139],"recognition":[12,140],"and":[13,33,50,109,124,141,147],"translation":[14,142],"tasks.":[15],"Instead":[16],"of":[17,21],"the":[18,57,83,122,134],"traditional":[19],"approach":[20],"on":[24,40,93,121,129],"short":[25],"segments":[26,132],"containing":[27],"only":[28],"lowercase":[29],"or":[30],"partial":[31],"punctuation":[32,49,108],"capitalization":[34,110],"(PnC)":[35],"sentences,":[36],"we":[37,86],"propose":[38],"longer":[41,95,130],"utterances":[42],"that":[43,88],"include":[44],"complete":[45],"sentences":[46],"with":[47,67,74,80],"proper":[48],"capitalization.":[51],"We":[52],"achieve":[53],"this":[54],"by":[55],"using":[56],"FastConformer":[58],"architecture":[59],"which":[60],"allows":[61],"1":[63],"Billion":[64],"parameter":[65],"sequences":[68,94],"up":[69],"to":[70],"60":[71],"seconds":[72,98],"long":[73],"full":[75],"attention.":[76],"However,":[77],"while":[78],"PnC":[81],"enhances":[82],"overall":[84,135],"performance,":[85],"observed":[87],"accuracy":[89,137],"plateaus":[90],"when":[91],"than":[96],"40":[97],"across":[99,138],"various":[100],"evaluation":[101],"settings.":[102],"Our":[103],"proposed":[104],"significantly":[106],"improves":[107],"accuracy,":[111],"showing":[112],"25%":[114],"relative":[115],"word":[116],"error":[117],"rate":[118],"(WER)":[119],"improvement":[120],"Earnings-21":[123],"Earnings-22":[125],"benchmarks.":[126,143],"Additionally,":[127],"audio":[131],"increases":[133],"model":[136,145],"The":[144],"weights":[146],"code":[149],"are":[150],"open-sourced":[151],"though":[152],"NVIDIA":[153],"NeMo.<sup":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155,158,160,162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[156],"<sup":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup><sup":[159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/NVIDIA/NeMo<sup":[161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>https://huggingface.co/nvidia/parakeet-tdt_ctc-1.1b":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}