{"id":"https://openalex.org/W2075517979","doi":"https://doi.org/10.1109/iscslp.2012.6423524","title":"Improved unit selection speech synthesis method utilizing subjective evaluation results on synthetic speech","display_name":"Improved unit selection speech synthesis method utilizing subjective evaluation results on synthetic speech","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2075517979","doi":"https://doi.org/10.1109/iscslp.2012.6423524","mag":"2075517979"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5091584895","display_name":"Xianjun Xia","orcid":"https://orcid.org/0000-0001-5277-6634"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Jun Xia","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology of China, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology of China, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678003","display_name":"Chenyu Yang","orcid":"https://orcid.org/0000-0001-9997-4929"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen-Yu Yang","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology of China, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology of China, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3292,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84070114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"160","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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":0.9940999746322632,"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/speech-synthesis","display_name":"Speech synthesis","score":0.889037013053894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825954556465149},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7671447992324829},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6709542870521545},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5976729989051819},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5480490326881409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48996701836586},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4509158730506897},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3232036232948303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09215095639228821}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.889037013053894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825954556465149},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7671447992324829},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6709542870521545},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5976729989051819},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5480490326881409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48996701836586},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4509158730506897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3232036232948303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09215095639228821},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W38285298","https://openalex.org/W1965555277","https://openalex.org/W1973766695","https://openalex.org/W2144317449","https://openalex.org/W2150658333","https://openalex.org/W2171292466","https://openalex.org/W2403351921","https://openalex.org/W6601598784","https://openalex.org/W6713743917"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W1914543332","https://openalex.org/W4245668640","https://openalex.org/W2032843702","https://openalex.org/W2388979876","https://openalex.org/W4206187606","https://openalex.org/W2032960563","https://openalex.org/W2142993035"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,51],"improved":[4],"unit":[5,32,77,128],"selection":[6,33,129],"and":[7,15,105,121],"waveform":[8],"concatenation":[9],"speech":[10,42,74,81,89,159],"synthesis":[11,34,82,110],"method":[12,152],"by":[13,29,54,133],"gathering":[14],"utilizing":[16],"human":[17],"feedbacks":[18],"on":[19,96,160],"synthetic":[20,41,62,92,107,136,158],"speech.":[21,108],"Firstly,":[22],"a":[23,47,161],"set":[24],"of":[25,149,157,163],"texts":[26],"are":[27,64,131],"synthesized":[28,116],"the":[30,40,72,103,112,118,122,134,141,147,155],"baseline":[31,119],"system.":[35],"Each":[36],"prosodic":[37],"word":[38],"within":[39],"is":[43,84,99,115],"then":[44],"evaluated":[45,132],"as":[46,66],"natural":[48,61,104],"one":[49,53],"or":[50],"unnatural":[52,106],"listeners.":[55],"In":[56],"our":[57,150],"proposed":[58,151],"method,":[59],"these":[60],"segments":[63],"treated":[65],"virtual":[67],"candidate":[68],"units":[69],"to":[70,139],"extend":[71],"original":[73],"corpus":[75],"for":[76],"selection.":[78],"A":[79,91],"new":[80],"system":[83,120,124],"constructed":[85],"using":[86,102,117],"this":[87],"extended":[88,123],"corpus.":[90],"error":[93,137],"detector":[94,138],"based":[95],"SVM":[97],"classifier":[98],"also":[100],"built":[101],"At":[109],"time,":[111],"input":[113],"text":[114],"simultaneously.":[125],"The":[126],"two":[127],"results":[130,145],"trained":[135],"determine":[140],"optimal":[142],"one.":[143],"Experimental":[144],"prove":[146],"effectiveness":[148],"in":[153],"improving":[154],"naturalness":[156],"task":[162],"synthesizing":[164],"place":[165],"names.":[166]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}