{"id":"https://openalex.org/W4296069275","doi":"https://doi.org/10.21437/interspeech.2022-10802","title":"Strategies for developing a Conversational Speech Dataset for Text-To-Speech Synthesis","display_name":"Strategies for developing a Conversational Speech Dataset for Text-To-Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069275","doi":"https://doi.org/10.21437/interspeech.2022-10802"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10802","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10802","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10138/355892","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071288294","display_name":"Adaeze O. Adigwe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adaeze O. Adigwe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109914325","display_name":"Esther Klabbers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esther Klabbers","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5062,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63905223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2318","last_page":"2322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9713000059127808,"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":0.9713000059127808,"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/T12031","display_name":"Speech and dialogue systems","score":0.9510999917984009,"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":0.7931106090545654},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.689834713935852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6427115201950073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5031701922416687},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.44959935545921326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3895197808742523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931106090545654},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.689834713935852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6427115201950073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5031701922416687},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.44959935545921326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3895197808742523}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10802","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10802","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/355892","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/355892","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference article"}],"best_oa_location":{"id":"pmh:oai:helda.helsinki.fi:10138/355892","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/355892","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W4397292310","https://openalex.org/W127416991","https://openalex.org/W2500421879","https://openalex.org/W2184371793","https://openalex.org/W2186688931","https://openalex.org/W4205598694","https://openalex.org/W2537969829","https://openalex.org/W2389032213","https://openalex.org/W2356192947"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"many":[3],"efforts":[4],"to":[5,37,49,92],"improve":[6],"the":[7,25,38,82],"quality":[8],"of":[9,21,81],"speech":[10,27,60,96],"synthesis":[11,97],"systems":[12,18],"in":[13,85,98],"conversational":[14,99],"AI.":[15],"Although":[16],"state-of-the-art":[17],"are":[19],"capable":[20],"producing":[22],"natural-sounding":[23],"speech,":[24],"generated":[26],"often":[28],"lacks":[29],"prosodic":[30,77],"variation":[31],"and":[32,78,88],"is":[33],"not":[34],"always":[35],"suited":[36],"task.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"examine":[44],"dialogue":[45],"data":[46,53,83,94],"collection":[47],"methods":[48],"use":[50],"as":[51],"training":[52],"for":[54,95],"our":[55],"acoustic":[56],"models.":[57],"We":[58,75],"collect":[59,93],"using":[61],"three":[62],"different":[63],"setups:":[64],"(1)":[65],"Random":[66],"read-aloud":[67],"sentences;":[68],"(2)":[69],"Performed":[70],"dialogues;":[71],"(3)":[72],"Semi-Spontaneous":[73],"dialogues.":[74],"analyze":[76],"textual":[79],"properties":[80],"collected":[84],"these":[86],"setups":[87],"make":[89],"some":[90],"recommendations":[91],"AI":[100],"settings.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}