{"id":"https://openalex.org/W4313159336","doi":"https://doi.org/10.1109/iicaiet55139.2022.9936815","title":"A Hybrid TDNN-HMM Automatic Speech Recognizer for Filipino Children's Speech","display_name":"A Hybrid TDNN-HMM Automatic Speech Recognizer for Filipino Children's Speech","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4313159336","doi":"https://doi.org/10.1109/iicaiet55139.2022.9936815"},"language":"en","primary_location":{"id":"doi:10.1109/iicaiet55139.2022.9936815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet55139.2022.9936815","pdf_url":null,"source":{"id":"https://openalex.org/S4363608273","display_name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","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/A5000846068","display_name":"John Andrew Ing","orcid":null},"institutions":[{"id":"https://openalex.org/I5996616","display_name":"De La Salle University","ror":"https://ror.org/04xftk194","country_code":"PH","type":"education","lineage":["https://openalex.org/I5996616"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"John Andrew Y. Ing","raw_affiliation_strings":["College of Computer Studies, De La Salle University,Manila,Philippines","College of Computer Studies, De La Salle University, Manila, Philippines"],"affiliations":[{"raw_affiliation_string":"College of Computer Studies, De La Salle University,Manila,Philippines","institution_ids":["https://openalex.org/I5996616"]},{"raw_affiliation_string":"College of Computer Studies, De La Salle University, Manila, Philippines","institution_ids":["https://openalex.org/I5996616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039652944","display_name":"Ronald M. Pascual","orcid":null},"institutions":[{"id":"https://openalex.org/I5996616","display_name":"De La Salle University","ror":"https://ror.org/04xftk194","country_code":"PH","type":"education","lineage":["https://openalex.org/I5996616"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ronald M. Pascual","raw_affiliation_strings":["College of Computer Studies, De La Salle University,Manila,Philippines","College of Computer Studies, De La Salle University, Manila, Philippines"],"affiliations":[{"raw_affiliation_string":"College of Computer Studies, De La Salle University,Manila,Philippines","institution_ids":["https://openalex.org/I5996616"]},{"raw_affiliation_string":"College of Computer Studies, De La Salle University, Manila, Philippines","institution_ids":["https://openalex.org/I5996616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016621085","display_name":"Francis D. Dimzon","orcid":null},"institutions":[{"id":"https://openalex.org/I5996616","display_name":"De La Salle University","ror":"https://ror.org/04xftk194","country_code":"PH","type":"education","lineage":["https://openalex.org/I5996616"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Francis D. Dimzon","raw_affiliation_strings":["College of Computer Studies, De La Salle University,Manila,Philippines","College of Computer Studies, De La Salle University, Manila, Philippines"],"affiliations":[{"raw_affiliation_string":"College of Computer Studies, De La Salle University,Manila,Philippines","institution_ids":["https://openalex.org/I5996616"]},{"raw_affiliation_string":"College of Computer Studies, De La Salle University, Manila, Philippines","institution_ids":["https://openalex.org/I5996616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000846068"],"corresponding_institution_ids":["https://openalex.org/I5996616"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59801756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.9211795926094055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7977663278579712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703232765197754},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.596954345703125},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5728676915168762},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5354269742965698},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5140146017074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5074548125267029},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4585859477519989},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4497518241405487},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3092840313911438}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9211795926094055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7977663278579712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703232765197754},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.596954345703125},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5728676915168762},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5354269742965698},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5140146017074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074548125267029},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4585859477519989},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4497518241405487},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3092840313911438},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iicaiet55139.2022.9936815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet55139.2022.9936815","pdf_url":null,"source":{"id":"https://openalex.org/S4363608273","display_name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W12796654","https://openalex.org/W1491356416","https://openalex.org/W1524333225","https://openalex.org/W1616590059","https://openalex.org/W1894807994","https://openalex.org/W1971734011","https://openalex.org/W2098950223","https://openalex.org/W2108696621","https://openalex.org/W2117671523","https://openalex.org/W2125838338","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2168171912","https://openalex.org/W2193413348","https://openalex.org/W2402146185","https://openalex.org/W2509129594","https://openalex.org/W2727162590","https://openalex.org/W2954573175","https://openalex.org/W2963303951","https://openalex.org/W2972425557","https://openalex.org/W3094651650","https://openalex.org/W3129427077","https://openalex.org/W3134320148","https://openalex.org/W3163152557","https://openalex.org/W4302557958","https://openalex.org/W6600520985","https://openalex.org/W6631362777","https://openalex.org/W6676567526","https://openalex.org/W6712930963","https://openalex.org/W6740821810","https://openalex.org/W6768282385"],"related_works":["https://openalex.org/W99997047","https://openalex.org/W2057483569","https://openalex.org/W2584084702","https://openalex.org/W2026749810","https://openalex.org/W2903098319","https://openalex.org/W2572828648","https://openalex.org/W4313159336","https://openalex.org/W2793122029","https://openalex.org/W4244902868","https://openalex.org/W1971793356"],"abstract_inverted_index":{"Previous":[0],"studies":[1,29],"presented":[2],"in":[3,6],"the":[4,7,12,34,49,85,151,154,161,167],"literature":[5],"recent":[8],"years":[9],"have":[10],"shown":[11],"feasibility":[13],"of":[14,27,51,75,91,99,137,153,173],"developing":[15],"an":[16,133],"automatic":[17],"speech":[18],"recognition":[19],"(ASR)":[20],"system":[21,55],"for":[22],"Filipino-speaking":[23],"children.":[24],"However,":[25],"most":[26],"these":[28],"are":[30,142],"solely":[31],"based":[32],"on":[33,93],"Hidden":[35],"Markov":[36],"Model":[37,42],"(HMM)":[38],"with":[39],"Gaussian":[40],"Mixture":[41],"(GMM).":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"present":[48,146],"development":[50],"a":[52,126],"hybrid":[53,164],"ASR":[54],"using":[56],"both":[57],"HMM":[58,100,140],"and":[59,82,102,117],"Time":[60],"Delay":[61],"Neural":[62],"Network":[63],"(TDNN).":[64],"The":[65,156],"Filipino":[66],"Children's":[67],"Speech":[68],"Corpus":[69],"(FCSC),":[70],"which":[71],"is":[72,160],"purely":[73],"composed":[74],"read":[76],"speech,":[77],"was":[78],"used":[79],"to":[80],"train":[81],"test":[83],"all":[84],"models.":[86],"We":[87,144],"performed":[88],"several":[89],"sets":[90],"experiments":[92,123],"various":[94,97,103],"phoneme":[95],"sets,":[96],"numbers":[98],"states,":[101],"enhanced":[104],"models":[105],"that":[106,125,147,165],"employed":[107],"vocal":[108],"tract":[109],"length":[110],"normalization":[111],"(VTLN),":[112],"linear":[113],"discriminant":[114],"analysis":[115],"(LDA),":[116],"speaker":[118],"adaptive":[119],"training":[120],"(SAT).":[121],"Our":[122],"show":[124],"basic":[127],"TDNN-HMM":[128,163],"model":[129,135,159],"could":[130],"consistently":[131],"outperform":[132],"HMM-GMM":[134],"regardless":[136],"how":[138],"many":[139],"states":[141],"present.":[143],"also":[145],"VTLN":[148],"slightly":[149],"enhances":[150],"performance":[152],"model.":[155],"best":[157],"performing":[158],"4-state":[162],"obtained":[166],"lowest":[168],"word":[169],"error":[170],"rate":[171],"(WER)":[172],"0.97%.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-05T23:21:25.405358","created_date":"2025-10-10T00:00:00"}