{"id":"https://openalex.org/W3169874582","doi":"https://doi.org/10.21437/interspeech.2021-341","title":"RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis","display_name":"RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3169874582","doi":"https://doi.org/10.21437/interspeech.2021-341","mag":"3169874582"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.08468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051282919","display_name":"Rohola Zandie","orcid":null},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohola Zandie","raw_affiliation_strings":["University of Denver, Denver, United States"],"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, United States","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041948053","display_name":"Mohammad H. Mahoor","orcid":"https://orcid.org/0000-0001-8923-4660"},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad H. Mahoor","raw_affiliation_strings":["University of Denver, Denver, United States"],"affiliations":[{"raw_affiliation_string":"University of Denver, Denver, United States","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012077093","display_name":"Julia Madsen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Madsen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027407793","display_name":"Eshrat S. Emamian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eshrat S. Emamian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051282919"],"corresponding_institution_ids":["https://openalex.org/I131651094"],"apc_list":null,"apc_paid":null,"fwci":0.1398,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53754264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"2751","last_page":"2755"},"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":0.9986000061035156,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7910194396972656},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6744356751441956},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6564268469810486},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6102969646453857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6060030460357666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5396873950958252},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5364314913749695},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5208300352096558},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5132067203521729},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4799407124519348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4393247067928314},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.41558778285980225},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.060382336378097534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910194396972656},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6744356751441956},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6564268469810486},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6102969646453857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6060030460357666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5396873950958252},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5364314913749695},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5208300352096558},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5132067203521729},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4799407124519348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4393247067928314},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.41558778285980225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.060382336378097534},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-341","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.08468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08468","pdf_url":"https://arxiv.org/pdf/2106.08468","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3169874582","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.08468.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.08468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.08468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.08468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08468","pdf_url":"https://arxiv.org/pdf/2106.08468","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169874582.pdf","grobid_xml":"https://content.openalex.org/works/W3169874582.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1498897359","https://openalex.org/W1597121597","https://openalex.org/W2101045344","https://openalex.org/W2394761397","https://openalex.org/W2398973091","https://openalex.org/W2527729766","https://openalex.org/W2608207374","https://openalex.org/W2946200149","https://openalex.org/W2971737394","https://openalex.org/W2972557612","https://openalex.org/W3003338281","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3025165719","https://openalex.org/W3030437843","https://openalex.org/W3130016944","https://openalex.org/W3141839452","https://openalex.org/W3177989406"],"related_works":["https://openalex.org/W3197824033","https://openalex.org/W3093185524","https://openalex.org/W430347950","https://openalex.org/W2032286903","https://openalex.org/W2972359262","https://openalex.org/W2740729892","https://openalex.org/W3029923669","https://openalex.org/W3031221932","https://openalex.org/W2765486990","https://openalex.org/W2000167159","https://openalex.org/W201998811","https://openalex.org/W1593359196","https://openalex.org/W2787350905","https://openalex.org/W1713240683","https://openalex.org/W3031408054","https://openalex.org/W2981454799","https://openalex.org/W2911845330","https://openalex.org/W2038562847","https://openalex.org/W3088421464","https://openalex.org/W2969049672"],"abstract_inverted_index":{"This":[0,84],"paper":[1],"introduces":[2],"RyanSpeech,":[3],"a":[4,39,74,101,116],"new":[5],"speech":[6,30,45,51,79,113],"corpus":[7,46,138],"for":[8,38,92,103,142],"research":[9],"on":[10,118],"automated":[11],"text-to-speech":[12],"(TTS)":[13],"systems.":[14],"Publicly":[15],"available":[16,43],"TTS":[17,94],"corpora":[18],"are":[19],"often":[20],"noisy,":[21],"recorded":[22,80],"with":[23],"multiple":[24],"speakers,":[25],"or":[26],"lack":[27],"quality":[28],"male":[29,44,76],"data.":[31],"In":[32],"order":[33],"to":[34],"meet":[35],"the":[36,48,137],"need":[37],"high":[40],"quality,":[41],"publicly":[42],"within":[47],"field":[49],"of":[50,73],"recognition,":[52],"we":[53,109],"have":[54,134],"designed":[55],"and":[56,87,107,115,139],"created":[57],"RyanSpeech":[58,90],"which":[59],"contains":[60],"textual":[61],"materials":[62,68],"from":[63],"real-world":[64,97],"conversational":[65],"settings.":[66],"These":[67],"contain":[69],"over":[70],"10":[71],"hours":[72],"professional":[75],"voice":[77],"actor's":[78],"at":[81],"44.1":[82],"kHz.":[83],"corpus's":[85],"design":[86],"pipeline":[88],"make":[89],"ideal":[91],"developing":[93],"systems":[95],"in":[96,124,129],"applications.":[98],"To":[99],"provide":[100],"baseline":[102],"future":[104],"research,":[105],"protocols,":[106],"benchmarks,":[108],"trained":[110,140],"4":[111],"state-of-the-art":[112],"models":[114,141],"vocoder":[117],"RyanSpeech.":[119],"The":[120],"results":[121],"show":[122],"3.36":[123],"mean":[125],"opinion":[126],"scores":[127],"(MOS)":[128],"our":[130],"best":[131],"model.":[132],"We":[133],"made":[135],"both":[136],"public":[143],"use.":[144]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}