{"id":"https://openalex.org/W2808087148","doi":"https://doi.org/10.1109/icsda.2017.8384451","title":"Developing a speech corpus from web news for Myanmar (Burmese) language","display_name":"Developing a speech corpus from web news for Myanmar (Burmese) language","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2808087148","doi":"https://doi.org/10.1109/icsda.2017.8384451","mag":"2808087148"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","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/A5034039876","display_name":"Aye Nyein Mon","orcid":null},"institutions":[{"id":"https://openalex.org/I80293557","display_name":"University of Computer Studies Yangon","ror":"https://ror.org/019ad8130","country_code":"MM","type":"education","lineage":["https://openalex.org/I80293557"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Aye Nyein Mon","raw_affiliation_strings":["Natural Language Processing Lab., University of Computer Studies, Yangon (UCSY), Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natural Language Processing Lab., University of Computer Studies, Yangon (UCSY), Myanmar","institution_ids":["https://openalex.org/I80293557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038930719","display_name":"Win Pa Pa","orcid":null},"institutions":[{"id":"https://openalex.org/I80293557","display_name":"University of Computer Studies Yangon","ror":"https://ror.org/019ad8130","country_code":"MM","type":"education","lineage":["https://openalex.org/I80293557"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Win Pa Pa","raw_affiliation_strings":["Natural Language Processing Lab., University of Computer Studies, Yangon, UCSY, Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natural Language Processing Lab., University of Computer Studies, Yangon, UCSY, Myanmar","institution_ids":["https://openalex.org/I80293557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083674619","display_name":"Ye Kyaw Thu","orcid":null},"institutions":[{"id":"https://openalex.org/I193620225","display_name":"Okayama Prefectural University","ror":"https://ror.org/038bgk418","country_code":"JP","type":"education","lineage":["https://openalex.org/I193620225"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ye Kyaw Thu","raw_affiliation_strings":["Artificial Intelligence Lab., Okayama Prefectural University (OpU), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab., Okayama Prefectural University (OpU), Japan","institution_ids":["https://openalex.org/I193620225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066309896","display_name":"Yoshinori Sagisakaa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Sagisakaa","raw_affiliation_strings":["Waseda Daigaku, Shinjuku-ku, Tokyo, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Daigaku, Shinjuku-ku, Tokyo, JP","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.685,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92621205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"ii","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":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.8084170818328857},{"id":"https://openalex.org/keywords/burmese","display_name":"Burmese","score":0.7965904474258423},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6949194669723511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6102704405784607},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5582390427589417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5454626083374023},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5184776186943054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005180835723877},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.49945545196533203},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.28676748275756836},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19187882542610168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084170818328857},{"id":"https://openalex.org/C2779443383","wikidata":"https://www.wikidata.org/wiki/Q9228","display_name":"Burmese","level":2,"score":0.7965904474258423},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6949194669723511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6102704405784607},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5582390427589417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5454626083374023},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5184776186943054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005180835723877},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.49945545196533203},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28676748275756836},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19187882542610168},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2017.8384451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W105675387","https://openalex.org/W775622597","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1975640689","https://openalex.org/W2203871458","https://openalex.org/W2289846468","https://openalex.org/W2577358322","https://openalex.org/W6604221329","https://openalex.org/W6631362777","https://openalex.org/W6732952302"],"related_works":["https://openalex.org/W3096124370","https://openalex.org/W2784059283","https://openalex.org/W3011423644","https://openalex.org/W3150298331","https://openalex.org/W3031221932","https://openalex.org/W2574832780","https://openalex.org/W2976274203","https://openalex.org/W2008737763","https://openalex.org/W2291624303","https://openalex.org/W2101694857"],"abstract_inverted_index":{"Speech":[0],"corpus":[1,46,74,94,119],"is":[2,42,48,59,120],"important":[3],"for":[4,26,51,75],"statistical":[5],"model":[6],"based":[7],"automatic":[8,52],"speech":[9,18,24,45,53,73,89,93,100,118],"recognition":[10,54,90],"and":[11,35,69,107,114,129,147],"it":[12,36],"reflects":[13],"the":[14,23,67,76],"performance":[15],"of":[16,22,71,96],"a":[17,60],"recognizer.":[19],"Although":[20],"most":[21],"corpora":[25],"resource-riched":[27],"languages":[28],"such":[29],"as":[30],"English":[31],"are":[32,109],"widely":[33],"available":[34,50],"can":[37],"be":[38,80],"used":[39],"easily,":[40],"there":[41,108],"no":[43],"Myanmar":[44,58,72,87],"which":[47],"freely":[49],"(ASR)":[55],"research":[56],"since":[57],"low":[61],"resource":[62],"language.":[63],"This":[64],"paper":[65],"presents":[66],"design":[68],"development":[70],"news":[77,106],"domain":[78],"to":[79,82],"applied":[81],"convolutional":[83],"neural":[84],"network":[85],"(CNN)-based":[86],"continuous":[88],"research.":[91],"The":[92],"consists":[95],"20":[97],"hours":[98],"read":[99],"data":[101],"collected":[102],"from":[103],"online":[104],"web":[105],"178":[110],"speakers":[111],"(126":[112],"females":[113],"52":[115],"males).":[116],"Our":[117],"evaluated":[121],"on":[122,145,149],"two":[123],"test":[124],"sets:":[125],"TestSet1":[126,146],"(web":[127],"data)":[128],"TestSet2":[130],"(news":[131],"recording":[132],"with":[133],"10":[134],"natives).":[135],"Using":[136],"CNN-based":[137],"model,":[138],"word":[139],"error":[140],"rate":[141],"(WER)":[142],"achieves":[143],"24.73%":[144],"22.95%":[148],"TestSet2.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}