{"id":"https://openalex.org/W3198020407","doi":"https://doi.org/10.21437/interspeech.2021-1599","title":"Hi-Fi Multi-Speaker English TTS Dataset","display_name":"Hi-Fi Multi-Speaker English TTS Dataset","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198020407","doi":"https://doi.org/10.21437/interspeech.2021-1599","mag":"3198020407"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1599","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/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":true,"raw_author_name":"Evelina Bakhturina","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/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"],"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/A5049524014","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-0572-705X"},"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":"Yang Zhang","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066445347"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":7.3423,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97649768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2776","last_page":"2780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9936000108718872,"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/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.705857515335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.554840087890625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42309021949768066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35035213828086853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705857515335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.554840087890625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42309021949768066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35035213828086853}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1599","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W2166637769","https://openalex.org/W2404126548","https://openalex.org/W2808706139","https://openalex.org/W2960427821","https://openalex.org/W2963300588","https://openalex.org/W2963691546","https://openalex.org/W2972359262","https://openalex.org/W2973072704","https://openalex.org/W2974231335","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3015537910","https://openalex.org/W3015645837","https://openalex.org/W3021066808","https://openalex.org/W3025013833","https://openalex.org/W3030437843","https://openalex.org/W3043783436","https://openalex.org/W3092028330","https://openalex.org/W3095545636","https://openalex.org/W3128910262","https://openalex.org/W3141854550","https://openalex.org/W3144259191","https://openalex.org/W3150572638","https://openalex.org/W4232345992","https://openalex.org/W4287231588"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,60,69],"new":[4,27],"multi-speaker":[5],"English":[6],"dataset":[7,12,28,78],"for":[8],"training":[9],"text-to-speech":[10],"models.The":[11],"is":[13,79],"based":[14],"on":[15],"Lib-riVox":[16],"audiobooks":[17],"and":[18,68],"Project":[19],"Gutenberg":[20],"texts,":[21],"both":[22],"in":[23],"the":[24],"public":[25],"domain.The":[26],"contains":[29],"about":[30],"292":[31],"hours":[32,42],"of":[33,63,73],"speech":[34,50],"from":[35],"10":[36],"speakers":[37],"with":[38,52,59],"at":[39,46,64,74,82],"least":[40,65,75],"17":[41],"per":[43],"speaker":[44],"sampled":[45],"44.1":[47],"kHz.To":[48],"select":[49],"samples":[51],"high":[53],"quality,":[54],"we":[55],"considered":[56],"audio":[57],"recordings":[58],"signal":[61],"bandwidth":[62],"13":[66],"kHz":[67],"signal-to-noise":[70],"ratio":[71],"(SNR)":[72],"32":[76],"dB.The":[77],"publicly":[80],"released":[81],"\"http://www.openslr.org/109/\".":[83]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
