{"id":"https://openalex.org/W4392903704","doi":"https://doi.org/10.1109/icassp48485.2024.10447120","title":"Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context","display_name":"Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903704","doi":"https://doi.org/10.1109/icassp48485.2024.10447120"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447120","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":"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/A5068307574","display_name":"Wei Kang","orcid":"https://orcid.org/0000-0003-0193-2654"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435428","display_name":"Xiaoyu Yang","orcid":"https://orcid.org/0000-0002-3570-8979"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066643565","display_name":"Zengwei Yao","orcid":"https://orcid.org/0000-0002-2331-2387"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004231067","display_name":"Fangjun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743978","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-3313-5473"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102707172","display_name":"Liyong Guo","orcid":"https://orcid.org/0009-0002-2465-3914"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006167","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-3246-0039"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5068307574"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":8.6046,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98040523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10991","last_page":"10995"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/punctuation","display_name":"Punctuation","score":0.9076836109161377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047807812690735},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7893739938735962},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6648927330970764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6288146376609802},{"id":"https://openalex.org/keywords/casing","display_name":"Casing","score":0.6129080653190613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5415502190589905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5009844303131104},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.47655895352363586},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11483028531074524},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0918569564819336}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9076836109161377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047807812690735},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7893739938735962},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6648927330970764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6288146376609802},{"id":"https://openalex.org/C30399818","wikidata":"https://www.wikidata.org/wiki/Q5048830","display_name":"Casing","level":2,"score":0.6129080653190613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5415502190589905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5009844303131104},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.47655895352363586},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11483028531074524},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0918569564819336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447120","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":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2024490156","https://openalex.org/W2067974452","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2995181338","https://openalex.org/W3015686596","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3197478142","https://openalex.org/W3198694222","https://openalex.org/W3208887030","https://openalex.org/W4214671568","https://openalex.org/W4226420874","https://openalex.org/W4286895682","https://openalex.org/W4307106469","https://openalex.org/W4372349774","https://openalex.org/W4375869165","https://openalex.org/W4387799863","https://openalex.org/W6631190155","https://openalex.org/W6636915900","https://openalex.org/W6639156005","https://openalex.org/W6799174933"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W2365703075"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,66,145],"introduce":[4],"Libriheavy,":[5],"a":[6,68],"large-scale":[7],"ASR":[8],"corpus":[9,32],"consisting":[10],"of":[11,14,24,33,101],"50,000":[12],"hours":[13],"read":[15],"English":[16],"speech":[17,34],"derived":[18],"from":[19,38,117],"LibriVox.":[20],"To":[21],"the":[22,29,78,102,111,118,138],"best":[23],"our":[25,147],"knowledge,":[26],"Libriheavy":[27,47,92],"is":[28,124],"largest":[30],"freely-available":[31],"with":[35],"supervisions.":[36],"Different":[37],"other":[39,157],"open-sourced":[40],"datasets":[41],"that":[42],"only":[43],"provide":[44],"normalized":[45],"transcriptions,":[46],"contains":[48],"richer":[49],"information":[50],"such":[51],"as":[52,90],"punctuation,":[53],"casing":[54],"and":[55,70,76,113,121,128,141],"text":[56],"context,":[57],"which":[58,151],"brings":[59],"more":[60],"flexibility":[61],"for":[62],"system":[63],"building.":[64],"Specifically,":[65],"propose":[67],"general":[69],"efficient":[71],"pipeline":[72,150],"to":[73,84,156],"locate,":[74],"align":[75],"segment":[77],"audios":[79,120],"in":[80,130],"previously":[81],"published":[82],"Librilight":[83],"its":[85],"corresponding":[86],"texts.":[87],"The":[88],"same":[89],"Librilight,":[91],"also":[93,109,153],"has":[94],"three":[95],"training":[96,131],"subsets":[97],"small,":[98],"medium,":[99],"large":[100],"sizes":[103],"500h,":[104],"5000h,":[105],"50000h":[106],"respectively.":[107],"We":[108],"extract":[110],"dev":[112],"test":[114],"evaluation":[115],"sets":[116],"aligned":[119],"guarantee":[122],"there":[123],"no":[125],"overlapping":[126],"speakers":[127],"books":[129],"sets.":[132],"Baseline":[133],"systems":[134],"are":[135],"built":[136],"on":[137],"popular":[139],"CTC-Attention":[140],"transducer":[142],"models.":[143],"Additionally,":[144],"open-source":[146],"dataset":[148],"creatation":[149],"can":[152],"be":[154],"used":[155],"audio":[158],"alignment":[159],"tasks.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}