{"id":"https://openalex.org/W4414865238","doi":"https://doi.org/10.3390/informatics12040107","title":"Integrating Speech Recognition into Intelligent Information Systems: From Statistical Models to Deep Learning","display_name":"Integrating Speech Recognition into Intelligent Information Systems: From Statistical Models to Deep Learning","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4414865238","doi":"https://doi.org/10.3390/informatics12040107"},"language":"en","primary_location":{"id":"doi:10.3390/informatics12040107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics12040107","pdf_url":"https://www.mdpi.com/2227-9709/12/4/107/pdf?version=1759568527","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2227-9709/12/4/107/pdf?version=1759568527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113385244","display_name":"Chaoji Wu","orcid":"https://orcid.org/0009-0006-6764-4048"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoji Wu","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China"],"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111890180","display_name":"Yi Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Pan","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China"],"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077402107","display_name":"Hsin\u2010Kai Wu","orcid":"https://orcid.org/0000-0003-0018-9969"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipan Wu","raw_affiliation_strings":["College of Physics and Opto-Electronic Engineering, Shenzhen University, Shenzhen 518060, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Opto-Electronic Engineering, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048210153","display_name":"Lei Ning","orcid":"https://orcid.org/0000-0003-0019-9761"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ning","raw_affiliation_strings":["College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China"],"affiliations":[{"raw_affiliation_string":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111890180"],"corresponding_institution_ids":["https://openalex.org/I4210152380"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1505039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"4","first_page":"107","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.25189998745918274,"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":0.25189998745918274,"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/deep-learning","display_name":"Deep learning","score":0.7458000183105469},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7387999892234802},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5490000247955322},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5475999712944031},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5074999928474426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43389999866485596},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.3804999887943268},{"id":"https://openalex.org/keywords/intelligent-decision-support-system","display_name":"Intelligent decision support system","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7458000183105469},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7387999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226999998092651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6546000242233276},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4659999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/informatics12040107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics12040107","pdf_url":"https://www.mdpi.com/2227-9709/12/4/107/pdf?version=1759568527","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:952253b18e4a4e5e8550185915805e31","is_oa":true,"landing_page_url":"https://doaj.org/article/952253b18e4a4e5e8550185915805e31","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics, Vol 12, Iss 4, p 107 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/informatics12040107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics12040107","pdf_url":"https://www.mdpi.com/2227-9709/12/4/107/pdf?version=1759568527","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414865238.pdf","grobid_xml":"https://content.openalex.org/works/W4414865238.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"has":[4],"advanced":[5],"rapidly,":[6],"evolving":[7,149],"from":[8],"early":[9],"template-matching":[10],"systems":[11,146],"to":[12,101,136],"modern":[13],"deep":[14,34],"learning":[15,35,45],"frameworks.":[16],"This":[17],"review":[18],"systematically":[19],"traces":[20],"ASR\u2019s":[21],"technological":[22],"evolution":[23],"across":[24],"four":[25],"phases:":[26],"the":[27,33,38,138],"template-based":[28],"era,":[29],"statistical":[30],"modeling":[31],"approaches,":[32],"revolution,":[36],"and":[37,65,71,96,104,115,127,143],"emergence":[39],"of":[40,140],"large-scale":[41],"models":[42,55,59,70],"under":[43],"diverse":[44],"paradigms.":[46],"We":[47,107],"analyze":[48],"core":[49],"technologies":[50],"such":[51,121],"as":[52,122],"hidden":[53],"Markov":[54],"(HMMs),":[56],"Gaussian":[57],"mixture":[58],"(GMMs),":[60],"recurrent":[61],"neural":[62],"networks":[63],"(RNNs),":[64],"recent":[66],"architectures":[67],"including":[68],"Transformer-based":[69],"Wav2Vec":[72],"2.0.":[73],"Beyond":[74],"algorithmic":[75],"development,":[76],"we":[77,131],"examine":[78],"how":[79],"ASR":[80,145],"integrates":[81],"into":[82],"intelligent":[83,144],"information":[84],"systems,":[85,95],"analyzing":[86],"real-world":[87],"applications":[88],"in":[89],"healthcare,":[90],"education,":[91],"smart":[92],"homes,":[93],"enterprise":[94],"automotive":[97],"domains":[98],"with":[99],"attention":[100],"deployment":[102,116],"considerations":[103],"system":[105],"design.":[106],"also":[108],"address":[109],"persistent":[110],"challenges\u2014noise":[111],"robustness,":[112],"low-resource":[113],"adaptation,":[114],"efficiency\u2014while":[117],"exploring":[118],"emerging":[119],"solutions":[120],"multimodal":[123],"fusion,":[124],"privacy-preserving":[125],"modeling,":[126],"lightweight":[128],"architectures.":[129],"Finally,":[130],"outline":[132],"future":[133],"research":[134],"directions":[135],"guide":[137],"development":[139],"robust,":[141],"scalable,":[142],"for":[147],"complex,":[148],"environments.":[150]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-10-10T00:00:00"}