{"id":"https://openalex.org/W2898019480","doi":"https://doi.org/10.1145/3264746.3264801","title":"Phoneme segmentation using deep learning for speech synthesis","display_name":"Phoneme segmentation using deep learning for speech synthesis","publication_year":2018,"publication_date":"2018-10-09","ids":{"openalex":"https://openalex.org/W2898019480","doi":"https://doi.org/10.1145/3264746.3264801","mag":"2898019480"},"language":"en","primary_location":{"id":"doi:10.1145/3264746.3264801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264746.3264801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","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/A5101410938","display_name":"Young Han Lee","orcid":"https://orcid.org/0000-0001-8200-2867"},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Han Lee","raw_affiliation_strings":["Korea Electronics Technology Institute, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute, Republic of Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011318032","display_name":"Yang Jong-Yeol","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Yeol Yang","raw_affiliation_strings":["Korea Electronics Technology Institute, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute, Republic of Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006431171","display_name":"Choongsang Cho","orcid":"https://orcid.org/0000-0001-5952-5491"},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choongsang Cho","raw_affiliation_strings":["Korea Electronics Technology Institute, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute, Republic of Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026805915","display_name":"Hyedong Jung","orcid":"https://orcid.org/0009-0005-0848-6097"},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyedong Jung","raw_affiliation_strings":["Korea Electronics Technology Institute, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute, Republic of Korea","institution_ids":["https://openalex.org/I4210131650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210131650"],"apc_list":null,"apc_paid":null,"fwci":0.5069,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74662337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"61"},"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":0.9958999752998352,"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":0.9937999844551086,"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":0.8012052774429321},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7636147737503052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7399293780326843},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6493178606033325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6265219449996948},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5972317457199097},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5305144190788269},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5039698481559753},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47907334566116333},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44285061955451965},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4371940493583679},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4345182478427887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4306025505065918},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4105141758918762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08395975828170776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012052774429321},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7636147737503052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7399293780326843},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6493178606033325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6265219449996948},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5972317457199097},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5305144190788269},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5039698481559753},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47907334566116333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44285061955451965},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4371940493583679},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4345182478427887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4306025505065918},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4105141758918762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08395975828170776},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3264746.3264801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264746.3264801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1570629387","https://openalex.org/W1922655562","https://openalex.org/W1990505856","https://openalex.org/W2143612262","https://openalex.org/W2591927543","https://openalex.org/W2806733747","https://openalex.org/W2963609956","https://openalex.org/W4256161595"],"related_works":["https://openalex.org/W1980401417","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W1558302546"],"abstract_inverted_index":{"In":[0,54],"this":[1,44],"paper,":[2],"we":[3,28,46],"propose":[4],"the":[5,13,30,36,57,69],"phoneme":[6,52,71],"segmentation":[7],"method,":[8],"which":[9,65],"is":[10,66],"one":[11],"of":[12,51],"basic":[14],"module":[15],"that":[16],"consist":[17],"unit-selection-based":[18],"speech":[19,38,40],"synthesis,":[20],"using":[21],"deep":[22],"learning":[23],"algorithm.":[24],"To":[25],"enhance":[26],"this,":[27],"apply":[29],"additional":[31],"cross":[32],"entropy":[33],"loss":[34],"into":[35],"Deep":[37],"based":[39],"recognition":[41],"architecture.":[42],"From":[43],"approach,":[45],"can":[47],"get":[48],"higher":[49,67],"accuracy":[50,64],"boundary.":[53],"our":[55],"experiments,":[56],"proposed":[58],"method":[59],"has":[60],"20.91":[61],"%":[62],"boundary":[63],"than":[68],"conventional":[70],"segmentation.":[72]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}