{"id":"https://openalex.org/W4391021797","doi":"https://doi.org/10.1109/asru57964.2023.10389666","title":"LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of End-to-End ASR Models","display_name":"LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of End-to-End ASR Models","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021797","doi":"https://doi.org/10.1109/asru57964.2023.10389666"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5110285595","display_name":"A. Meister","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aleksandr Meister","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia","NVIDIA, Yerevan, Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086673602","display_name":"Matvey Novikov","orcid":"https://orcid.org/0000-0003-3124-3702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matvei Novikov","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia","NVIDIA, Yerevan, Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066709803","display_name":"Nikolay Karpov","orcid":"https://orcid.org/0000-0003-1053-5239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Karpov","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia","NVIDIA, Yerevan, Armenia"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066445347","display_name":"Evelina Bakhturina","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":"Evelina Bakhturina","raw_affiliation_strings":["NVIDIA,Santa Clara,USA","NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"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":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA,Santa Clara,USA","NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","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","NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110285595"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3903,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85579437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9993000030517578,"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/punctuation","display_name":"Punctuation","score":0.9848507642745972},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7755322456359863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302002906799316},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.6942075490951538},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5800970196723938},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.4499345123767853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3994908630847931},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35740411281585693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27916419506073},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1872624158859253},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11494287848472595},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06909650564193726}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9848507642745972},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7755322456359863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302002906799316},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.6942075490951538},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5800970196723938},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.4499345123767853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3994908630847931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35740411281585693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27916419506073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1872624158859253},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11494287848472595},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06909650564193726},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2398104528","https://openalex.org/W2610127012","https://openalex.org/W2908510526","https://openalex.org/W2962989741","https://openalex.org/W2963979492","https://openalex.org/W3011222885","https://openalex.org/W3094965760","https://openalex.org/W3097777922","https://openalex.org/W3108216882","https://openalex.org/W3174269049","https://openalex.org/W3183246637","https://openalex.org/W3198777455","https://openalex.org/W4225297945","https://openalex.org/W4284974527","https://openalex.org/W4285221485","https://openalex.org/W4311000453","https://openalex.org/W6609799775","https://openalex.org/W6631190155","https://openalex.org/W6635223454","https://openalex.org/W6757817989","https://openalex.org/W6785859737","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2936002343","https://openalex.org/W2370831213","https://openalex.org/W2188883480","https://openalex.org/W2013684995","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Traditional":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"models":[5,36,120],"output":[6],"lower-cased":[7],"words":[8],"without":[9],"punctuation":[10,40,64,78,95,110],"marks,":[11,111],"which":[12],"reduces":[13],"readability":[14],"and":[15,41,52,79,96,112,119],"necessitates":[16],"a":[17,27,71,90,98],"subsequent":[18],"text":[19],"processing":[20],"model":[21],"to":[22,48,75],"convert":[23],"ASR":[24,35,85],"transcripts":[25],"into":[26],"proper":[28],"format.":[29],"Simultaneously,":[30],"the":[31,55,77],"development":[32],"of":[33,38,63,83],"end-to-end":[34,84],"capable":[37],"predicting":[39],"capitalization":[42,80],"presents":[43],"several":[44],"challenges,":[45],"primarily":[46],"due":[47],"limited":[49],"data":[50],"availability":[51],"shortcomings":[53],"in":[54],"existing":[56],"evaluation":[57,100],"methods,":[58],"such":[59],"as":[60],"inadequate":[61],"assessment":[62],"prediction.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"introduce":[70],"LibriSpeech-PC":[72,91],"benchmark":[73,88],"designed":[74],"assess":[76],"prediction":[81],"capabilities":[82],"models.":[86,115],"The":[87],"includes":[89],"dataset":[92],"with":[93],"restored":[94],"capitalization,":[97],"novel":[99],"metric":[101],"called":[102],"Punctuation":[103],"Error":[104],"Rate":[105],"(PER)":[106],"that":[107],"focuses":[108],"on":[109],"initial":[113],"baseline":[114],"All":[116],"code,":[117],"data,":[118],"are":[121],"publicly":[122],"available.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}