{"id":"https://openalex.org/W2021083801","doi":"https://doi.org/10.1109/iscslp.2014.6936574","title":"The Vietnamese speech recognition based on rectified linear units deep neural network and spoken term detection system combination","display_name":"The Vietnamese speech recognition based on rectified linear units deep neural network and spoken term detection system combination","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2021083801","doi":"https://doi.org/10.1109/iscslp.2014.6936574","mag":"2021083801"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th 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/A5021081307","display_name":"Shifu Xiong","orcid":"https://orcid.org/0000-0003-4759-147X"},"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":true,"raw_author_name":"Shifu Xiong","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"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":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060287819","display_name":"Diyuan Liu","orcid":null},"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":"Diyuan Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021081307"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.842741,"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":"183","last_page":"186"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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":0.8170207738876343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7500004768371582},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7096766233444214},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5989977717399597},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5188773274421692},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5171031951904297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4914900064468384},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4890816807746887},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.48276200890541077},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4723580777645111},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45871713757514954},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4545648396015167},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4356175661087036},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4027402997016907},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3657325208187103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170207738876343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7500004768371582},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7096766233444214},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5989977717399597},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5188773274421692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5171031951904297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4914900064468384},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4890816807746887},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.48276200890541077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4723580777645111},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45871713757514954},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4545648396015167},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4356175661087036},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4027402997016907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3657325208187103},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W23025778","https://openalex.org/W1648698152","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2028956843","https://openalex.org/W2052274902","https://openalex.org/W2062227835","https://openalex.org/W2086754356","https://openalex.org/W2103635001","https://openalex.org/W2116110832","https://openalex.org/W2128212935","https://openalex.org/W2142401923","https://openalex.org/W2442329935","https://openalex.org/W6600906190","https://openalex.org/W6637086781","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2955724459","https://openalex.org/W2037769829","https://openalex.org/W2096389830","https://openalex.org/W2163537793","https://openalex.org/W1499383998","https://openalex.org/W2140351598","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2402899696"],"abstract_inverted_index":{"In":[0,120],"this":[1],"paper,":[2],"we":[3,50,101,124],"report":[4],"our":[5,148],"recent":[6],"progress":[7],"on":[8,27,164],"the":[9,17,28,46,52,93,121,131],"under-resource":[10],"language":[11],"automatic":[12,80],"speech":[13],"recognition":[14,57],"(ASR)":[15],"and":[16,33,62,70,109,129,157],"following":[18,53],"spoken":[19],"term":[20,140],"detection":[21],"(STD).":[22],"The":[23],"experiments":[24],"are":[25,65],"carried":[26],"National":[29],"Institute":[30],"of":[31,95,97,133],"Standards":[32],"Technology":[34],"(NIST)":[35],"Open":[36],"Keyword":[37],"Search":[38],"2013":[39],"(OpenKWS13)":[40],"evaluation":[41],"Vietnamese":[42,74,166],"corpus.":[43],"Compared":[44],"with":[45],"conventional":[47],"ASR":[48,135],"system,":[49],"made":[51],"modifications":[54],"to":[55,67,91,137],"improve":[56],"accuracy.":[58],"First,":[59],"pitch":[60,69],"features":[61],"tone":[63,71],"modeling":[64],"applied":[66],"cover":[68],"information":[72],"since":[73],"is":[75,86],"a":[76],"tonal":[77],"language.":[78],"Second,":[79],"question":[81],"generation":[82],"for":[83,88],"decision":[84],"tree":[85],"used":[87],"state":[89],"tying":[90],"address":[92],"problem":[94],"lack":[96],"linguistic":[98],"knowledge.":[99],"Finally,":[100],"investigate":[102],"rectified":[103],"linear":[104],"units":[105],"(ReLUs)":[106],"activation":[107],"function":[108],"cross-lingual":[110],"pre-training":[111],"in":[112],"deep":[113],"neural":[114],"network":[115],"(DNN)":[116],"acoustic":[117],"model":[118],"training.":[119],"STD":[122,161],"procedure,":[123],"adopt":[125],"term-dependent":[126],"score":[127],"normalization":[128],"combine":[130],"outputs":[132],"diverse":[134],"systems":[136],"increase":[138],"actual":[139],"weighted":[141],"value":[142],"(ATWV).":[143],"After":[144],"applying":[145],"these":[146],"methods,":[147],"current":[149],"best":[150],"single":[151],"system":[152,162],"achieves":[153],"48.32%":[154],"word":[155],"accuracy":[156],"0.398":[158],"ATWV":[159],"after":[160],"combination":[163],"OpenKWS13":[165],"development":[167],"set.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}