{"id":"https://openalex.org/W2044081012","doi":"https://doi.org/10.1109/ncc.2014.6811333","title":"A probabilistic approach to selecting units for speech synthesis based on acoustic similarity","display_name":"A probabilistic approach to selecting units for speech synthesis based on acoustic similarity","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W2044081012","doi":"https://doi.org/10.1109/ncc.2014.6811333","mag":"2044081012"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2014.6811333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2014.6811333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Twentieth National Conference on Communications (NCC)","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/A5089591508","display_name":"Anjana Babu","orcid":null},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anjana Babu","raw_affiliation_strings":["School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi"],"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","institution_ids":["https://openalex.org/I9579091"]},{"raw_affiliation_string":"School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078167741","display_name":"Karunakaran Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K Raghava Krishnan","raw_affiliation_strings":["School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","Department of Electrical Engineering, Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","institution_ids":["https://openalex.org/I9579091"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025998364","display_name":"Anil Kumar Sao","orcid":"https://orcid.org/0000-0001-5316-5528"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil K Sao","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Madras","School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]},{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema A Murthy","raw_affiliation_strings":["School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","Department of Computer Science and Engineering, Indian Institute of Technology Madras"],"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, Indian Institute of Technology Mandi","institution_ids":["https://openalex.org/I9579091"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Madras","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089591508"],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73926277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"6"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9269487261772156},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7693993449211121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259727716445923},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6701905727386475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5669162273406982},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5296509265899658},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5093889832496643},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48300397396087646},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4684099555015564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44638490676879883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.349406361579895}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9269487261772156},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7693993449211121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259727716445923},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6701905727386475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5669162273406982},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5296509265899658},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5093889832496643},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48300397396087646},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4684099555015564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44638490676879883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349406361579895},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.1109/ncc.2014.6811333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2014.6811333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Twentieth National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321071","display_name":"Department of Electronics and Information Technology, Ministry of Communications and Information Technology","ror":"https://ror.org/02z31cn83"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W101968188","https://openalex.org/W178225857","https://openalex.org/W1496801689","https://openalex.org/W1510007267","https://openalex.org/W1553896573","https://openalex.org/W1964600646","https://openalex.org/W1975433801","https://openalex.org/W1995332880","https://openalex.org/W2015876361","https://openalex.org/W2016760603","https://openalex.org/W2034383468","https://openalex.org/W2128704269","https://openalex.org/W2150658333","https://openalex.org/W2575483272","https://openalex.org/W2578832979","https://openalex.org/W6604082041","https://openalex.org/W6732119548"],"related_works":["https://openalex.org/W2255642176","https://openalex.org/W2067665617","https://openalex.org/W2559039559","https://openalex.org/W2181773877","https://openalex.org/W3015707856","https://openalex.org/W2227587554","https://openalex.org/W2133918396","https://openalex.org/W4319586549","https://openalex.org/W2188723525","https://openalex.org/W4283016115"],"abstract_inverted_index":{"Most":[0],"unit":[1,20],"selection":[2],"synthesisers":[3,33,68],"sound":[4,19],"quite":[5],"natural":[6],"when":[7,37],"the":[8,17,44,77,91,96,118,129,172],"database":[9],"consists":[10],"of":[11,14,16,25,48,72,160],"a":[12,22,38,64,70],"number":[13,24,71],"realisations":[15],"same":[18],"from":[21],"large":[23],"contexts.":[26],"A":[27,104],"common":[28],"problem":[29],"observed":[30],"with":[31],"these":[32],"is":[34,41,51,89,99,107,131,179],"unexpected":[35],"prosody":[36],"new":[39],"context":[40,79,93,98,122,130],"presented":[42],"in":[43,86,120,164,168],"text.":[45],"The":[46,83,148],"objective":[47],"this":[49,54,87],"paper":[50,88],"to":[52,63,80,140,162,171],"address":[53],"issue":[55],"and":[56,126,143,166],"select":[57,81],"appropriate":[58],"units":[59,111],"that":[60,90,175],"are":[61],"relevant":[62],"specific":[65],"context.":[66],"Text-to-speech":[67],"propose":[69],"different":[73],"features":[74],"based":[75,112],"on":[76,113,154],"linguistic":[78,97,177],"units.":[82],"key":[84],"contribution":[85],"acoustic":[92,115,121],"rather":[94],"than":[95],"crucial":[100],"for":[101,109],"improving":[102],"naturalness.":[103],"probabilistic":[105],"framework":[106],"proposed":[108,149],"selecting":[110],"an":[114],"framework.":[116],"Reducing":[117],"variability":[119],"improves":[123],"both":[124],"naturalness":[125],"intelligibility.":[127],"Since":[128],"only":[132],"specified":[133],"by":[134],"acoustics,":[135],"it":[136],"can":[137],"be":[138],"applied":[139],"any":[141],"language":[142],"perhaps":[144],"even":[145],"multilingual":[146],"synthesis.":[147],"approach":[150],"has":[151],"been":[152],"tested":[153],"2":[155],"Indian":[156],"languages.":[157],"An":[158],"improvement":[159],"up":[161],"21.9%":[163],"DMOS":[165],"73.93%":[167],"WER":[169],"relative":[170],"conventional":[173],"system":[174],"uses":[176],"criteria":[178],"observed.":[180]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}