{"id":"https://openalex.org/W4378364105","doi":"https://doi.org/10.1109/isdfs58141.2023.10131755","title":"Development of Low-Latency and Real-Time Filipino Children Automatic Speech Recognition System using Deep Neural Network","display_name":"Development of Low-Latency and Real-Time Filipino Children Automatic Speech Recognition System using Deep Neural Network","publication_year":2023,"publication_date":"2023-05-11","ids":{"openalex":"https://openalex.org/W4378364105","doi":"https://doi.org/10.1109/isdfs58141.2023.10131755"},"language":"en","primary_location":{"id":"doi:10.1109/isdfs58141.2023.10131755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isdfs58141.2023.10131755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Symposium on Digital Forensics and Security (ISDFS)","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/A5092023126","display_name":"Bonry Dorado","orcid":null},"institutions":[{"id":"https://openalex.org/I95350115","display_name":"Technological Institute of the Philippines","ror":"https://ror.org/02p79p790","country_code":"PH","type":"education","lineage":["https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"Bonry Dorado","raw_affiliation_strings":["Technological Institute of the Philippines,Graduate School,Quezon City,Philippines","Graduate School, Technological Institute of the Philippines, Quezon City, Philippines"],"affiliations":[{"raw_affiliation_string":"Technological Institute of the Philippines,Graduate School,Quezon City,Philippines","institution_ids":["https://openalex.org/I95350115"]},{"raw_affiliation_string":"Graduate School, Technological Institute of the Philippines, Quezon City, Philippines","institution_ids":["https://openalex.org/I95350115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067987211","display_name":"Alonica Villanueva","orcid":"https://orcid.org/0009-0003-4453-5103"},"institutions":[{"id":"https://openalex.org/I95350115","display_name":"Technological Institute of the Philippines","ror":"https://ror.org/02p79p790","country_code":"PH","type":"education","lineage":["https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Alonica Villanueva","raw_affiliation_strings":["Technological Institute of the Philippines,Graduate School,Quezon City,Philippines","Graduate School, Technological Institute of the Philippines, Quezon City, Philippines"],"affiliations":[{"raw_affiliation_string":"Technological Institute of the Philippines,Graduate School,Quezon City,Philippines","institution_ids":["https://openalex.org/I95350115"]},{"raw_affiliation_string":"Graduate School, Technological Institute of the Philippines, Quezon City, Philippines","institution_ids":["https://openalex.org/I95350115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5092023126"],"corresponding_institution_ids":["https://openalex.org/I95350115"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78000311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"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":0.9969000220298767,"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":0.9969000220298767,"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":0.9904000163078308,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.9513000249862671,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798380434513092},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.794283390045166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7857298851013184},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6462903618812561},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5288456678390503},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4988291263580322},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4979250431060791},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4809943437576294},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4409297704696655},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44071394205093384},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4242943525314331},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41931796073913574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41835668683052063},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.34777289628982544},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.320002943277359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798380434513092},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.794283390045166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7857298851013184},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6462903618812561},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5288456678390503},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4988291263580322},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4979250431060791},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4809943437576294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4409297704696655},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44071394205093384},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4242943525314331},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41931796073913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41835668683052063},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.34777289628982544},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.320002943277359},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isdfs58141.2023.10131755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isdfs58141.2023.10131755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 11th International Symposium on Digital Forensics and Security (ISDFS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1643818298","https://openalex.org/W2098950223","https://openalex.org/W2188958590","https://openalex.org/W2962146825","https://openalex.org/W3000339992","https://openalex.org/W3006260787","https://openalex.org/W3009116905","https://openalex.org/W3015611303","https://openalex.org/W3090128560","https://openalex.org/W3105925344","https://openalex.org/W3194316524","https://openalex.org/W3197373774","https://openalex.org/W4293054790","https://openalex.org/W4308083055","https://openalex.org/W6631362777","https://openalex.org/W6686855151","https://openalex.org/W6773172687"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W1987021544","https://openalex.org/W2376203252","https://openalex.org/W2620660273","https://openalex.org/W2122924390","https://openalex.org/W4378364105","https://openalex.org/W82600882","https://openalex.org/W2009810445"],"abstract_inverted_index":{"As":[0,126],"no":[1],"studies":[2],"have":[3],"been":[4],"made":[5],"yet":[6],"to":[7,23,30,44,85,108,121,206],"use":[8,24,40],"real-time":[9,41,254],"speakers":[10,43],"in":[11],"performing":[12],"the":[13,25,32,46,70,87,110,114,123,128,144,166,177,182,190,195,220],"Filipino":[14,49,76,130,222],"children":[15,27,42,50,131,223,255],"automatic":[16,51,89,132,224],"speech":[17,28,52,90,133,225,231],"recognition":[18,53,91,134,226,232],"system,":[19],"this":[20],"study":[21],"aims":[22],"available":[26],"corpus":[29],"train":[31,109,122],"system":[33,54,115,135,168,227],"using":[34,253],"Deep":[35],"Neural":[36],"Network":[37],"technology":[38],"and":[39,83,157,214,241],"test":[45],"proposed":[47,129,221],"low-latency":[48],"with":[55,102,160,172,181],"low":[56],"word":[57,184,208],"error":[58,185,209],"rate.":[59],"The":[60,93],"6.76":[61],"hours":[62],"of":[63,69,99,113,140,163,187,197,251],"raw":[64],"wav":[65],"files":[66],"from":[67],"University":[68],"Philippines":[71],"Digital":[72],"Signal":[73],"Processing":[74],"Laboratory":[75],"Children\u2019s":[77],"Speech":[78],"Corpus":[79],"is":[80,106,119,169],"pre-processed,":[81],"extracted,":[82],"trained":[84],"create":[86],"planned":[88],"system.":[92],"time":[94,104],"delay":[95],"neural":[96],"network":[97],"module":[98],"Kaldi":[100],"Toolkit":[101],"symmetrical":[103],"strides":[105],"used":[107,120],"acoustic":[111],"model":[112],"while":[116,143],"3-gram":[117],"approach":[118],"language":[124],"model.":[125],"results,":[127],"has":[136,153],"an":[137],"average":[138],"latency":[139],"0.5188":[141],"seconds":[142,155,162],"other":[145,229],"cloud-based":[146],"speech-to-text":[147,199],"applications":[148,200,233],"such":[149],"as":[150],"Google":[151,212,239],"Speech-To-Text":[152,213],"0.7217":[154],"delay,":[156],"Whisper":[158,217,246],"API":[159,247],"1.0420":[161],"lag.":[164],"Moreover,":[165],"said":[167],"also":[170,202],"evaluated":[171],"different":[173],"input":[174],"devices":[175],"having":[176,248],"Jabra":[178,192],"wired":[179,193],"headset":[180],"lowest":[183],"rate":[186,210],"1.49%.":[188],"Using":[189],"same":[191],"headset,":[194],"accuracy":[196,250],"online":[198,230],"are":[201],"computed":[203],"which":[204],"results":[205],"6.17%":[207],"for":[211,216],"11.28%":[215],"API.":[218],"Therefore,":[219],"outperforms":[228],"by":[234],"1.4":[235],"times":[236,243],"faster":[237,244],"than":[238,245],"Speech-to-Text":[240],"two":[242],"highest":[249],"98.51%":[252],"speakers.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}