{"id":"https://openalex.org/W2216396205","doi":"https://doi.org/10.1109/icsda.2015.7357876","title":"Tonal phoneme based model for Vietnamese LVCSR","display_name":"Tonal phoneme based model for Vietnamese LVCSR","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2216396205","doi":"https://doi.org/10.1109/icsda.2015.7357876","mag":"2216396205"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2015.7357876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2015.7357876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","raw_type":"proceedings-article"},"type":"preprint","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/A5100695013","display_name":"V\u0103n Huy Nguy\u1ec5n","orcid":"https://orcid.org/0000-0002-3021-3811"},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van Huy Nguyen","raw_affiliation_strings":["Electronic faculty, Thai Nguyen University of Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic faculty, Thai Nguyen University of Technology, Vietnam","institution_ids":["https://openalex.org/I4210115718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052741228","display_name":"Chi Mai Luong","orcid":"https://orcid.org/0000-0002-2559-2247"},"institutions":[{"id":"https://openalex.org/I4210126846","display_name":"Information Technology Laboratory","ror":"https://ror.org/0440c3437","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065","https://openalex.org/I4210126846"]},{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["US","VN"],"is_corresponding":false,"raw_author_name":"Chi Mai Luong","raw_affiliation_strings":["Institute of Information Technology (IOIT) Vietnam Academy of Science and Technology, Vietnam","Vietnam Academy of Science and Technology","Information, Communication and Technology Laboratory [Hanoi]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology (IOIT) Vietnam Academy of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I70349855"]},{"raw_affiliation_string":"Vietnam Academy of Science and Technology","institution_ids":["https://openalex.org/I70349855"]},{"raw_affiliation_string":"Information, Communication and Technology Laboratory [Hanoi]","institution_ids":["https://openalex.org/I4210126846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033545842","display_name":"Tat Thang Vu","orcid":null},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tat Thang Vu","raw_affiliation_strings":["Institute of Information Technology (IOIT) Vietnam Academy of Science and Technology, Vietnam","Institute of Information Technology (IOIT), Vietnam Academy of Science and Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology (IOIT) Vietnam Academy of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I70349855"]},{"raw_affiliation_string":"Institute of Information Technology (IOIT), Vietnam Academy of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2259,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90687346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.9983999729156494,"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":0.8131768703460693},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7988409996032715},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7694512605667114},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.691851019859314},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6749740242958069},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.6676269769668579},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6162852048873901},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5751054286956787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5170077085494995},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48638370633125305},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.467387318611145},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45475828647613525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4131210446357727},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07685941457748413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131768703460693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7988409996032715},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7694512605667114},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.691851019859314},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6749740242958069},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.6676269769668579},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6162852048873901},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5751054286956787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170077085494995},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48638370633125305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.467387318611145},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45475828647613525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4131210446357727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07685941457748413},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2015.7357876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2015.7357876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1970088388","https://openalex.org/W1995966271","https://openalex.org/W2025526196","https://openalex.org/W2087395764","https://openalex.org/W2154304575","https://openalex.org/W2295119550","https://openalex.org/W3028642772","https://openalex.org/W3203924265","https://openalex.org/W6601785968","https://openalex.org/W6649115928","https://openalex.org/W6777926273","https://openalex.org/W6802119673"],"related_works":["https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"algorithm":[4,30],"that":[5,79],"is":[6,31,63],"first":[7],"known":[8],"as":[9],"a":[10,19,54,59,66],"grapheme-to-phoneme":[11],"method":[12],"to":[13,18,34,52,94],"transform":[14],"any":[15],"Vietnamese":[16,72],"word":[17,89],"tonal":[20,24,44,83,104],"phoneme-based":[21],"pronunciation.":[22],"The":[23,46,76],"phoneme":[25,84],"set":[26],"produced":[27],"by":[28,86,108],"this":[29],"further":[32],"used":[33],"develop":[35,53],"some":[36],"acoustic":[37],"models":[38],"which":[39,62],"integrated":[40],"tone":[41],"information":[42,106],"and":[43,57,112],"feature.":[45],"processes":[47],"using":[48,97],"the":[49,80,95,98,101,114,118],"Kaldi":[50],"toolkit":[51],"LVCSR":[55],"system":[56,96],"extract":[58],"bottleneck":[60,115],"feature":[61,105,116],"calculated":[64],"from":[65],"trained":[67],"deep":[68],"neural":[69],"network":[70],"for":[71],"are":[73],"also":[74],"presented.":[75],"results":[77],"showed":[78],"use":[81,102],"of":[82,88,103,110,113],"improved":[85,107],"1.54%":[87],"error":[90],"rate":[91],"(WER)":[92],"compared":[93],"nontonal":[99],"phoneme,":[100],"4.65%":[109],"WER,":[111],"gave":[117],"best":[119],"WER":[120],"with":[121],"about":[122],"10%":[123],"improvement.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
