{"id":"https://openalex.org/W2766099356","doi":"https://doi.org/10.1109/sisy.2017.8080585","title":"Novel alignment method for DNN TTS training using HMM synthesis models","display_name":"Novel alignment method for DNN TTS training using HMM synthesis models","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2766099356","doi":"https://doi.org/10.1109/sisy.2017.8080585","mag":"2766099356"},"language":"en","primary_location":{"id":"doi:10.1109/sisy.2017.8080585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sisy.2017.8080585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","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/A5053625267","display_name":"Sini\u0161a Suzi\u0107","orcid":"https://orcid.org/0000-0002-0511-6729"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Sinisa Suzic","raw_affiliation_strings":["Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089151399","display_name":"Tijana Deli\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Tijana Delic","raw_affiliation_strings":["Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110585076","display_name":"Darko Pekar","orcid":"https://orcid.org/0000-0003-3026-8086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darko Pekar","raw_affiliation_strings":["AlfaNum Speech Technologies, Novi Sad, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AlfaNum Speech Technologies, Novi Sad, Serbia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070162823","display_name":"Vladimir Ostoji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Vladimir Ostojic","raw_affiliation_strings":["Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univerzitet u Novom Sadu, Novi Sad, Vojvodina, RS","institution_ids":["https://openalex.org/I170726198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4131,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73181474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"000271","last_page":"000276"},"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":0.998199999332428,"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":0.996399998664856,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9060660600662231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114540576934814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6763398051261902},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6408398151397705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5834759473800659},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5626867413520813},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5465443730354309},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4802180230617523},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4625157117843628},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42532384395599365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2991234064102173},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.12565061450004578}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9060660600662231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114540576934814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6763398051261902},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6408398151397705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834759473800659},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5626867413520813},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5465443730354309},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4802180230617523},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4625157117843628},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42532384395599365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2991234064102173},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.12565061450004578},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sisy.2017.8080585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sisy.2017.8080585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W114226241","https://openalex.org/W136864235","https://openalex.org/W207695133","https://openalex.org/W1841835177","https://openalex.org/W2018613638","https://openalex.org/W2098544461","https://openalex.org/W2111284386","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2244504200","https://openalex.org/W2400063444","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2523860356","https://openalex.org/W2598638573","https://openalex.org/W2625819531","https://openalex.org/W2949382160","https://openalex.org/W6638711925","https://openalex.org/W6674978160","https://openalex.org/W6712610176","https://openalex.org/W6739722483"],"related_works":["https://openalex.org/W1974738623","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W175280642"],"abstract_inverted_index":{"In":[0,39],"order":[1],"to":[2,102],"train":[3],"neural":[4],"networks":[5],"(NN)":[6],"for":[7],"text-to-speech":[8],"synthesis":[9],"(TTS),":[10],"phonetic":[11],"segmentation":[12,19],"must":[13],"be":[14],"performed.":[15],"The":[16],"most":[17],"accurate":[18],"is":[20,30,59,62],"performed":[21],"manually,":[22],"but":[23],"the":[24,92],"process":[25],"of":[26,98],"creating":[27],"manual":[28],"alignments":[29,89],"costly":[31],"and":[32],"time-consuming,":[33],"so":[34],"automatic":[35],"procedures":[36,71],"are":[37],"preferable.":[38],"this":[40,65],"paper,":[41],"a":[42],"simple":[43],"alignment":[44,70],"method":[45],"based":[46,55,72],"on":[47,73],"models":[48],"trained":[49,87,104],"during":[50],"hidden":[51],"Markov":[52],"Model":[53],"(HMM)":[54],"TTS":[56],"system":[57],"training":[58],"presented.":[60],"It":[61],"shown":[63],"that":[64,85],"approach":[66],"slightly":[67],"outperforms":[68],"standard":[69],"monophone":[74,106],"models.":[75],"Both":[76],"objective":[77],"measurements,":[78],"as":[79,81],"well":[80],"listening":[82],"tests,":[83],"show":[84],"NN":[86,103],"with":[88,91,105],"obtained":[90],"proposed":[93],"method,":[94],"can":[95],"produce":[96],"speech":[97],"higher":[99],"quality":[100],"compared":[101],"alignments.":[107]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}