{"id":"https://openalex.org/W40091564","doi":"https://doi.org/10.21437/interspeech.2010-594","title":"Evaluation of speaker mimic technology for personalizing SGD voices","display_name":"Evaluation of speaker mimic technology for personalizing SGD voices","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W40091564","doi":"https://doi.org/10.21437/interspeech.2010-594","mag":"40091564"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-594","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109914325","display_name":"Esther Klabbers","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092404","display_name":"InternetSpeech (United States)","ror":"https://ror.org/00f012347","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092404"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esther Klabbers","raw_affiliation_strings":["BioSpeech, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioSpeech, Inc","institution_ids":["https://openalex.org/I4210092404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066668295","display_name":"Alexander Kain","orcid":"https://orcid.org/0000-0001-5807-9311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kain","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041808115","display_name":"Jan P. H. van Santen","orcid":"https://orcid.org/0000-0003-3245-5301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan P. H. van Santen","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2737,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.42646959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2154","last_page":"2157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9944999814033508,"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":0.7777930498123169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7318558692932129},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6343493461608887},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5818380117416382},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.534986674785614},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5339965224266052},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5040068030357361},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.494457483291626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38691771030426025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38114285469055176},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3733636140823364},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1660516858100891},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0925055742263794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777930498123169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7318558692932129},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6343493461608887},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5818380117416382},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.534986674785614},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5339965224266052},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5040068030357361},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.494457483291626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38691771030426025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38114285469055176},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3733636140823364},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1660516858100891},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0925055742263794},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-594","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.7090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.7090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslu.ogi.edu/%7Ekain/pub/Klabbers2010-IS-SGD.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W5465423","https://openalex.org/W182786440","https://openalex.org/W1499275966","https://openalex.org/W1525540417","https://openalex.org/W1615777616","https://openalex.org/W1877213374","https://openalex.org/W2022554507","https://openalex.org/W2120260542","https://openalex.org/W2152024332","https://openalex.org/W2161964681","https://openalex.org/W2166637769","https://openalex.org/W2244925781"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"demonstrate":[4],"the":[5,25],"use":[6,46],"of":[7,27,33,66,89],"state-of-the-art":[8],"speech":[9,13],"technology":[10,72],"to":[11,18,31,45,56],"transform":[12,54],"from":[14,50,68],"a":[15,20,57,62,80,90],"source":[16],"speaker":[17,23,39,60],"mimic":[19],"particular":[21],"target":[22,59,105],"with":[24],"intention":[26],"providng":[28],"personalized":[29],"voices":[30,100],"users":[32,76],"Speech":[34],"Generating":[35],"Devices":[36],"(SGDs).":[37],"This":[38,71],"mimicry":[40],"(SM)":[41],"capability":[42],"allows":[43],"us":[44],"highquality":[47],"acoustic":[48],"inventories":[49],"professional":[51],"speakers":[52],"and":[53],"them":[55],"different":[58],"using":[61],"very":[63],"limited":[64,81],"set":[65],"sentences":[67],"that":[69,94],"speaker.":[70],"targets":[73],"future":[74],"SGD":[75],"who":[77],"still":[78],"have":[79],"vocabulary":[82],"or":[83],"available":[84],"previous":[85],"recordings.":[86],"The":[87],"results":[88],"perceptual":[91],"study":[92],"show":[93],"listeners":[95],"can":[96],"identify":[97],"which":[98],"SM":[99],"most":[101],"resemble":[102],"their":[103],"respective":[104],"voices.":[106],"1":[107]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}