{"id":"https://openalex.org/W2431323835","doi":"https://doi.org/10.1007/s40595-016-0071-3","title":"Speech classification using SIFT features on spectrogram images","display_name":"Speech classification using SIFT features on spectrogram images","publication_year":2016,"publication_date":"2016-06-16","ids":{"openalex":"https://openalex.org/W2431323835","doi":"https://doi.org/10.1007/s40595-016-0071-3","mag":"2431323835"},"language":"en","primary_location":{"id":"doi:10.1007/s40595-016-0071-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-016-0071-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-016-0071-3.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-016-0071-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102808845","display_name":"Quang Trung Nguyen","orcid":"https://orcid.org/0000-0001-9611-0551"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Quang Trung Nguyen","raw_affiliation_strings":["Human Machine Interaction Laboratory, University of Engineering and Technology, VNU Hanoi, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, University of Engineering and Technology, VNU Hanoi, Hanoi, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090494747","display_name":"The Duy Bui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"The Duy Bui","raw_affiliation_strings":["Human Machine Interaction Laboratory, University of Engineering and Technology, VNU Hanoi, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Human Machine Interaction Laboratory, University of Engineering and Technology, VNU Hanoi, Hanoi, Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102808845"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2211,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96484761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"4","first_page":"247","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9991999864578247,"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":0.9952999949455261,"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/spectrogram","display_name":"Spectrogram","score":0.8209521770477295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501416802406311},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6213412284851074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.601250171661377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5714573860168457},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49671870470046997},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.48970773816108704},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47522929310798645},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.47458553314208984},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4257052540779114},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.33065059781074524}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8209521770477295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501416802406311},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6213412284851074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.601250171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5714573860168457},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49671870470046997},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.48970773816108704},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47522929310798645},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.47458553314208984},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4257052540779114},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33065059781074524},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40595-016-0071-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-016-0071-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-016-0071-3.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ac1ac9eebdc44971b6a75efec7e4878f","is_oa":true,"landing_page_url":"https://doaj.org/article/ac1ac9eebdc44971b6a75efec7e4878f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vietnam Journal of Computer Science, Vol 3, Iss 4, Pp 247-257 (2016)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40595-016-0071-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40595-016-0071-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs40595-016-0071-3.pdf","source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2431323835.pdf","grobid_xml":"https://content.openalex.org/works/W2431323835.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1491473158","https://openalex.org/W1576767704","https://openalex.org/W1666984270","https://openalex.org/W1966297316","https://openalex.org/W1993882792","https://openalex.org/W1995562189","https://openalex.org/W2003115311","https://openalex.org/W2006586657","https://openalex.org/W2010710837","https://openalex.org/W2017427968","https://openalex.org/W2027922120","https://openalex.org/W2035305631","https://openalex.org/W2047411082","https://openalex.org/W2063223471","https://openalex.org/W2068247585","https://openalex.org/W2079912976","https://openalex.org/W2090431713","https://openalex.org/W2090861223","https://openalex.org/W2098299590","https://openalex.org/W2112048832","https://openalex.org/W2123783347","https://openalex.org/W2124386111","https://openalex.org/W2128160875","https://openalex.org/W2128716879","https://openalex.org/W2132037657","https://openalex.org/W2135704565","https://openalex.org/W2140785063","https://openalex.org/W2141965916","https://openalex.org/W2147768505","https://openalex.org/W2150423550","https://openalex.org/W2151103935","https://openalex.org/W2154236666","https://openalex.org/W2155126530","https://openalex.org/W2156375095","https://openalex.org/W2160815625","https://openalex.org/W2163829421","https://openalex.org/W2165115936","https://openalex.org/W2166742463","https://openalex.org/W2167986384","https://openalex.org/W2168249605","https://openalex.org/W2172097686","https://openalex.org/W2277036719","https://openalex.org/W2323591384","https://openalex.org/W2398826216","https://openalex.org/W2408093180","https://openalex.org/W2583512025","https://openalex.org/W4213171936","https://openalex.org/W4232478747"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W3034955165","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2049930962"],"abstract_inverted_index":{"Classification":[0],"of":[1,5,22,31,85,142],"speech":[2,11,33,52,74,86],"is":[3,148,158,182],"one":[4],"the":[6,20,24,32,40,109,126,143,146,165,172,178,180,183],"most":[7,30],"vital":[8],"problems":[9],"in":[10,139,153,185],"processing.":[12],"Although":[13],"there":[14],"have":[15,39,103],"been":[16],"many":[17],"studies":[18],"on":[19,82,125],"classification":[21,34,75,111],"speech,":[23],"results":[25,112],"are":[26,113,116,175],"still":[27],"limited.":[28],"Firstly,":[29],"approaches":[35],"requiring":[36],"input":[37],"data":[38,62,163],"same":[41],"dimension.":[42],"Secondly,":[43],"all":[44],"traditional":[45],"methods":[46],"must":[47,55],"be":[48,56],"trained":[49],"before":[50],"classifying":[51],"signal":[53,87],"and":[54,122],"retrained":[57],"when":[58],"having":[59],"more":[60,173,181],"training":[61,162,166],"or":[63],"new":[64],"class.":[65],"In":[66,151],"this":[67,107],"paper,":[68],"we":[69],"propose":[70],"an":[71],"approach":[72,97],"for":[73,160],"using":[76,99],"Scale-invariant":[77],"Feature":[78],"Transform":[79],"(SIFT)":[80],"features":[81,174],"spectrogram":[83],"images":[84],"combination":[88],"with":[89],"Local":[90],"na\u00efve":[91],"Bayes":[92],"nearest":[93],"neighbor.":[94],"The":[95,168],"proposed":[96,155],"allows":[98],"feature":[100],"vectors":[101],"to":[102,177],"different":[104],"sizes.":[105],"With":[106],"approach,":[108,156],"achieved":[110],"satisfactory.":[114],"They":[115],"73,":[117],"96,":[118],"95,":[119],"97":[120,123],"%,":[121],"%":[124],"ISOLET,":[127],"English":[128],"Isolated":[129],"Digits,":[130,134],"Vietnamese":[131,133],"Places,":[132],"JVPD":[135],"databases,":[136],"respectively.":[137],"Especially,":[138],"a":[140],"subset":[141],"TMW":[144],"database,":[145],"accuracy":[147,184],"100":[149],"%.":[150],"addition,":[152],"our":[154],"non-retraining":[157],"needed":[159],"additional":[161],"after":[164],"phase.":[167],"experiment":[169],"shows":[170],"that":[171],"added":[176],"model,":[179],"performance.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}