{"id":"https://openalex.org/W2292208301","doi":"https://doi.org/10.1186/s13636-016-0084-y","title":"Developing a unit selection voice given audio without corresponding text","display_name":"Developing a unit selection voice given audio without corresponding text","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2292208301","doi":"https://doi.org/10.1186/s13636-016-0084-y","mag":"2292208301"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-016-0084-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0084-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-016-0084-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-016-0084-y","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031027582","display_name":"Tejas Godambe","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tejas Godambe","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109274672","display_name":"Sai Krishna Rallabandi","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sai Krishna Rallabandi","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058673990","display_name":"Suryakanth V. Gangashetty","orcid":"https://orcid.org/0000-0001-6745-4363"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V. Gangashetty","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051008675","display_name":"A. Alkhairy","orcid":null},"institutions":[{"id":"https://openalex.org/I1284598098","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39","country_code":"SA","type":"facility","lineage":["https://openalex.org/I1284598098"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ashraf Alkhairy","raw_affiliation_strings":["King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I1284598098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103266450","display_name":"Afshan Jafri","orcid":"https://orcid.org/0000-0002-3841-7931"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Afshan Jafri","raw_affiliation_strings":["King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103266450"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.00798309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2016","issue":"1","first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7784179449081421},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6624813675880432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391921043395996},{"id":"https://openalex.org/keywords/impromptu","display_name":"Impromptu","score":0.6092215776443481},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4835805296897888},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4570380449295044},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44695010781288147},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43806952238082886},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4358433783054352},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4056411683559418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2753450870513916},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21881312131881714},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11548903584480286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784179449081421},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6624813675880432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391921043395996},{"id":"https://openalex.org/C2781454322","wikidata":"https://www.wikidata.org/wiki/Q6007730","display_name":"Impromptu","level":2,"score":0.6092215776443481},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4835805296897888},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4570380449295044},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44695010781288147},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43806952238082886},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4358433783054352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4056411683559418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2753450870513916},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21881312131881714},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11548903584480286},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-016-0084-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0084-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-016-0084-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-016-0084-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0084-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-016-0084-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3624210039","display_name":null,"funder_award_id":"10-INF1324-02","funder_id":"https://openalex.org/F4320335045","funder_display_name":"National Plan for Science, Technology and Innovation"}],"funders":[{"id":"https://openalex.org/F4320322997","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39"},{"id":"https://openalex.org/F4320335045","display_name":"National Plan for Science, Technology and Innovation","ror":"https://ror.org/02f81g417"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2292208301.pdf","grobid_xml":"https://content.openalex.org/works/W2292208301.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W16967297","https://openalex.org/W47863446","https://openalex.org/W64730254","https://openalex.org/W95152782","https://openalex.org/W178225857","https://openalex.org/W179090306","https://openalex.org/W202879582","https://openalex.org/W228314209","https://openalex.org/W1245895196","https://openalex.org/W1494198834","https://openalex.org/W1517939602","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1599623585","https://openalex.org/W1847897332","https://openalex.org/W1878590289","https://openalex.org/W1892788530","https://openalex.org/W1934041838","https://openalex.org/W1970101118","https://openalex.org/W1993952617","https://openalex.org/W2002342963","https://openalex.org/W2026369565","https://openalex.org/W2033010331","https://openalex.org/W2034537249","https://openalex.org/W2049686551","https://openalex.org/W2084609288","https://openalex.org/W2090755665","https://openalex.org/W2102499750","https://openalex.org/W2105961775","https://openalex.org/W2106554350","https://openalex.org/W2107457864","https://openalex.org/W2109862664","https://openalex.org/W2112285804","https://openalex.org/W2117849308","https://openalex.org/W2124629003","https://openalex.org/W2125496931","https://openalex.org/W2134659216","https://openalex.org/W2138550762","https://openalex.org/W2140918324","https://openalex.org/W2145880678","https://openalex.org/W2148154194","https://openalex.org/W2149062204","https://openalex.org/W2150658333","https://openalex.org/W2168510624","https://openalex.org/W2182936441","https://openalex.org/W2399277477","https://openalex.org/W2402146185","https://openalex.org/W2402788381","https://openalex.org/W2403351921","https://openalex.org/W2407760220","https://openalex.org/W2613330330","https://openalex.org/W2613407020","https://openalex.org/W2799061466","https://openalex.org/W2916018751","https://openalex.org/W2950186769","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W4388389884","https://openalex.org/W2157598242","https://openalex.org/W2037564206","https://openalex.org/W7946549","https://openalex.org/W2620660273","https://openalex.org/W2619911963","https://openalex.org/W2014474048","https://openalex.org/W2786927338","https://openalex.org/W22517275","https://openalex.org/W1554343988"],"abstract_inverted_index":{"Today,":[0],"a":[1,37,54,80,189,242,248,253,277],"large":[2,190],"amount":[3],"of":[4,15,56,69,76,227,269,276],"audio":[5,33,94,122,156],"data":[6,34,47,70,89,206,217],"is":[7,102],"available":[8,117],"on":[9,43,154,171,281],"the":[10,13,67,121,159,211,215,221,233,274,282],"web":[11],"in":[12,50,232,241,252,267],"form":[14],"audiobooks,":[16],"podcasts,":[17],"video":[18,20],"lectures,":[19],"blogs,":[21],"news":[22],"bulletins,":[23],"etc.":[24],"In":[25,184],"addition,":[26],"we":[27,142,187,229],"can":[28,64],"effortlessly":[29],"record":[30],"and":[31,52,61,72,99,126,139,161,168,179,218,247,261,264,271],"store":[32],"such":[35,90],"as":[36,91],"read,":[38],"lecture,":[39],"or":[40],"impromptu":[41],"speech":[42,195],"handheld":[44],"devices.":[45],"These":[46],"are":[48,83,96,109,116,131],"rich":[49],"prosody":[51],"provide":[53],"plethora":[55],"voices":[57,231],"to":[58,199],"choose":[59],"from,":[60],"their":[62],"availability":[63],"significantly":[65],"reduce":[66],"overhead":[68],"preparation":[71],"help":[73,275],"rapid":[74],"building":[75,136],"synthetic":[77,137],"voices.":[78],"But,":[79],"few":[81],"problems":[82],"associated":[84],"with":[85,214,273],"readily":[86],"using":[87,236,258],"this":[88,185],"(1)":[92,172],"these":[93],"files":[95],"generally":[97,164],"long,":[98],"audio-transcription":[100],"alignment":[101,157],"memory":[103],"intensive;":[104],"(2)":[105,176],"precise":[106],"corresponding":[107],"transcriptions":[108,115],"unavailable,":[110],"(3)":[111,180],"many":[112],"times,":[113],"no":[114],"at":[118],"all;":[119],"(4)":[120],"may":[123],"contain":[124],"dis-fluencies":[125],"non-speech":[127],"noises,":[128],"since":[129],"they":[130,146],"not":[132,148],"specifically":[133],"recorded":[134],"for":[135],"voices;":[138],"(5)":[140],"if":[141],"obtain":[143,200],"automatic":[144,194],"transcripts,":[145,201],"will":[147],"be":[149],"error":[150,182],"free.":[151],"Earlier":[152],"works":[153],"long":[155],"addressing":[158],"first":[160],"second":[162],"issue":[163],"preferred":[165],"reasonable":[166],"transcripts":[167],"mainly":[169],"focused":[170],"less":[173],"manual":[174],"intervention,":[175],"mispronunciation":[177],"detection,":[178],"segmentation":[181],"recovery.":[183],"work,":[186],"use":[188],"vocabulary":[191],"public":[192],"domain":[193],"recognition":[196],"(ASR)":[197],"system":[198],"followed":[202],"by":[203],"confidence":[204],"measure-based":[205],"pruning":[207],"which":[208],"together":[209],"address":[210],"five":[212],"issues":[213],"found":[216],"also":[219],"ensure":[220],"above":[222],"three":[223],"points.":[224],"For":[225],"proof":[226],"concept,":[228],"build":[230],"English":[234],"language":[235],"an":[237],"audiobook":[238],"(read":[239],"speech)":[240,251],"female":[243],"voice":[244,255],"from":[245,256],"LibriVox":[246],"lecture":[249],"(spontaneous":[250],"male":[254],"Coursera,":[257],"both":[259],"reference":[260],"hypotheses":[262],"transcriptions,":[263],"evaluate":[265],"them":[266],"terms":[268],"intelligibility":[270],"naturalness":[272],"perceptual":[278],"listening":[279],"test":[280],"Blizzard":[283],"2013":[284],"corpus.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
