{"id":"https://openalex.org/W169615514","doi":"https://doi.org/10.21437/interspeech.2009-438","title":"Personalizing synthetic voices for people with progressive speech disorders: judging voice similarity","display_name":"Personalizing synthetic voices for people with progressive speech disorders: judging voice similarity","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W169615514","doi":"https://doi.org/10.21437/interspeech.2009-438","mag":"169615514"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5091343291","display_name":"Sarah Creer","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. M. Creer","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013974933","display_name":"Stuart Cunningham","orcid":"https://orcid.org/0000-0001-9418-8726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. P. Cunningham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010560619","display_name":"Phil Green","orcid":"https://orcid.org/0000-0001-9103-7287"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. D. Green","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114234822","display_name":"K. Fatema","orcid":"https://orcid.org/0000-0001-7122-3904"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K. Fatema","raw_affiliation_strings":["University of Kent, Canterbury, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kent, Canterbury, United Kingdom","institution_ids":["https://openalex.org/I20581793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3589,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83627184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1427","last_page":"1430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9991999864578247,"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/speech-recognition","display_name":"Speech recognition","score":0.8119611740112305},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7601074576377869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695426344871521},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6170435547828674},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5474368929862976},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5340192914009094},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.504062294960022},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.42835015058517456},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41623252630233765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3680820167064667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32865631580352783},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2743690609931946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18565547466278076}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8119611740112305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7601074576377869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695426344871521},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6170435547828674},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5474368929862976},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5340192914009094},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.504062294960022},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.42835015058517456},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41623252630233765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3680820167064667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32865631580352783},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2743690609931946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18565547466278076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W187510402","https://openalex.org/W1984905644","https://openalex.org/W2049686551","https://openalex.org/W2396366106","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W1902557034"],"abstract_inverted_index":{"Abstract":[0],"Inbuildingpersonalized":[1],"syntheticvoicesforpeople":[2],"withspeechdisorders,":[3],"the":[4,8,52,62,77,93,96,109],"output":[5],"should":[6],"capture":[7],"individual\u2019s":[9],"vocal":[10],"iden-tity.":[11],"This":[12],"paper":[13],"reports":[14],"a":[15,48],"listener":[16],"judgment":[17],"experiment":[18],"on":[19],"thesimilarity":[20],"of":[21,31,43,54,98],"Hidden":[22],"Markov":[23],"Model":[24],"based":[25],"synthetic":[26],"voices":[27],"us-ing":[28],"varying":[29],"amounts":[30],"adaptation":[32],"data":[33,44,60],"to":[34,46,76,91,111],"two":[35],"non-impairedspeakers.":[36],"We":[37],"conclude":[38],"that":[39,50,82],"around":[40],"100":[41],"sentences":[42],"isneeded":[45],"build":[47],"voice":[49,124,126],"retains":[51],"characteristics":[53],"thetarget":[55],"speaker":[56],"but":[57,95],"using":[58,65],"more":[59],"improves":[61],"voice.":[63],"Experi-ments":[64],"Multi-Layer":[66],"Perceptrons":[67],"(MLPs)":[68],"are":[69],"conducted":[70],"to\ufb01nd":[71],"which":[72],"acoustic":[73],"features":[74,100],"contribute":[75,89],"similarity":[78],"judg-ments.":[79],"Results":[80],"show":[81],"mel-cepstral":[83],"distortion":[84],"and":[85],"fraction":[86],"ofvoicing":[87],"agreement":[88],"most":[90],"replicating":[92],"similarityjudgment":[94],"combination":[97],"all":[99],"is":[101],"required":[102],"for":[103,113],"ac-curate":[104],"prediction.":[105],"Ongoing":[106],"work":[107],"applies":[108],"\ufb01ndings":[110],"voicebuilding":[112],"people":[114],"with":[115],"impaired":[116],"speech.":[117],"Index":[118],"Terms":[119],":":[120],"HMM-based":[121],"speech":[122],"synthesis,":[123],"similaritymeasure,":[125],"banking":[127],"1.":[128],"Introduction":[129]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}