{"id":"https://openalex.org/W4390052822","doi":"https://doi.org/10.36647/ciml/04.02.a003","title":"An Overview of Speech-To-Text Conversion","display_name":"An Overview of Speech-To-Text Conversion","publication_year":2023,"publication_date":"2023-10-14","ids":{"openalex":"https://openalex.org/W4390052822","doi":"https://doi.org/10.36647/ciml/04.02.a003"},"language":"en","primary_location":{"id":"doi:10.36647/ciml/04.02.a003","doi":"https://doi.org/10.36647/ciml/04.02.a003","is_oa":true,"landing_page_url":"http://dx.doi.org/10.36647/ciml/04.02.a003","pdf_url":"https://www.cimachinelearning.com/assets/article/overview-speech-text-conversion.pdf","source":{"id":"https://openalex.org/S4387284221","display_name":"Computational Intelligence and Machine Learning","issn_l":"2582-7464","issn":["2582-7464"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Machine Learning","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.cimachinelearning.com/assets/article/overview-speech-text-conversion.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012857134","display_name":"Kartik Aggarwal","orcid":"https://orcid.org/0000-0003-3062-2364","observed_orcids":["https://orcid.org/0000-0003-3062-2364"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kartik Aggarwal","raw_affiliation_strings":["Dronacharya College of Engineering, Khentawas, Farrukh Nagar, Gurugram, Haryana, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dronacharya College of Engineering, Khentawas, Farrukh Nagar, Gurugram, Haryana, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5012857134"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10808037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/speech-to-text-conversion","display_name":"speech-to-text conversion","score":0.9599999785423279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7760000228881836},{"id":"https://openalex.org/keywords/voice-recognition-systems","display_name":"voice recognition systems","score":0.6779999732971191},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.843999981880188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/hearing-loss","display_name":"hearing loss","score":0.7710000276565552},{"id":"https://openalex.org/keywords/long-range-communication","display_name":"long-distance communication","score":0.7770000100135803},{"id":"https://openalex.org/keywords/vocal-performance-analysis","display_name":"vocal performance analysis","score":0.9490000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669450044631958},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6012817025184631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937726616859436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37906521558761597},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.34927260875701904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3449152112007141},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.21763601899147034},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17773976922035217}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.36647/ciml/04.02.a003","doi":"https://doi.org/10.36647/ciml/04.02.a003","is_oa":true,"landing_page_url":"http://dx.doi.org/10.36647/ciml/04.02.a003","pdf_url":"https://www.cimachinelearning.com/assets/article/overview-speech-text-conversion.pdf","source":{"id":"https://openalex.org/S4387284221","display_name":"Computational Intelligence and Machine Learning","issn_l":"2582-7464","issn":["2582-7464"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.36647/ciml/04.02.a003","doi":"https://doi.org/10.36647/ciml/04.02.a003","is_oa":true,"landing_page_url":"http://dx.doi.org/10.36647/ciml/04.02.a003","pdf_url":"https://www.cimachinelearning.com/assets/article/overview-speech-text-conversion.pdf","source":{"id":"https://openalex.org/S4387284221","display_name":"Computational Intelligence and Machine Learning","issn_l":"2582-7464","issn":["2582-7464"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390052822.pdf","grobid_xml":"https://content.openalex.org/works/W4390052822.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2902784055","https://openalex.org/W2952292837","https://openalex.org/W2958482258","https://openalex.org/W2979921809","https://openalex.org/W2997173210","https://openalex.org/W3005578234","https://openalex.org/W3015633994","https://openalex.org/W3015698636","https://openalex.org/W3016042119","https://openalex.org/W3017535695","https://openalex.org/W3091781323","https://openalex.org/W3116603504","https://openalex.org/W3139312241","https://openalex.org/W3139334914","https://openalex.org/W3161945002","https://openalex.org/W3170818378","https://openalex.org/W3176362845","https://openalex.org/W3176998001","https://openalex.org/W3177091091","https://openalex.org/W3194316524","https://openalex.org/W3195499629","https://openalex.org/W3205193540","https://openalex.org/W3205397926","https://openalex.org/W3208546935","https://openalex.org/W3209371554","https://openalex.org/W3209763111","https://openalex.org/W4205510032","https://openalex.org/W4210696221","https://openalex.org/W4212874332","https://openalex.org/W4213377284","https://openalex.org/W4214867895","https://openalex.org/W4221142789","https://openalex.org/W4224925623","https://openalex.org/W4224952687","https://openalex.org/W4225319992","https://openalex.org/W4226088164","https://openalex.org/W4226324628","https://openalex.org/W4243210529","https://openalex.org/W4246941507","https://openalex.org/W4285502369","https://openalex.org/W4289821117","https://openalex.org/W4293691046","https://openalex.org/W4293863190","https://openalex.org/W4300551547","https://openalex.org/W4312776332","https://openalex.org/W4312811746","https://openalex.org/W6959340700"],"related_works":["https://openalex.org/W6912723702","https://openalex.org/W2077728135","https://openalex.org/W3008924437","https://openalex.org/W4392945681","https://openalex.org/W203046623","https://openalex.org/W7171284349","https://openalex.org/W4408862527","https://openalex.org/W4377028381","https://openalex.org/W3008959354","https://openalex.org/W4322629454"],"abstract_inverted_index":{"As":[0],"a":[1,123,152],"result":[2],"of":[3,84,97,125,131,144,163,173],"developments":[4,87],"in":[5,40,71,79,90,106,110,146,176],"science":[6],"and":[7,47,150],"technology,":[8],"an":[9,177],"automatic":[10],"speech-to-text":[11,75],"(STT)":[12],"conversion":[13,76],"system":[14,19],"has":[15,101],"been":[16],"available.":[17],"This":[18],"converts":[20],"spoken":[21],"words":[22],"into":[23,113],"text":[24],"that":[25],"can":[26],"be":[27],"read":[28],"visually.":[29],"People":[30],"with":[31,136],"trouble":[32],"hearing":[33],"may":[34],"use":[35],"this":[36],"technology":[37],"to":[38,50,68,88,154,187],"communicate":[39],"other":[41],"ways,":[42],"including":[43],"understanding":[44],"voice":[45,184],"communication":[46],"being":[48],"able":[49],"follow":[51],"directions":[52],"using":[53],"their":[54,189],"visual":[55],"abilities.":[56],"There":[57],"are":[58,128],"instances":[59],"when":[60],"seeing":[61],"something":[62,114],"is":[63,77,94],"more":[64],"powerful":[65],"than":[66],"listening":[67],"something,":[69],"particularly":[70],"long-distance":[72],"communication;":[73],"thus,":[74],"crucial":[78],"situations":[80],"like":[81,115],"these.":[82],"One":[83],"the":[85,91,95,111,129,142,147,171],"fascinating":[86],"occur":[89],"twenty-first":[92],"century":[93],"advent":[96],"machine":[98,132],"learning.":[99,133],"It":[100],"evolved":[102],"from":[103,156],"its":[104,157],"roots":[105],"neurology":[107],"studies":[108],"conducted":[109],"1940s":[112],"artificial":[116],"intelligence":[117],"humans":[118],"have":[119],"created.":[120],"Neural":[121],"networks,":[122],"collection":[124],"complex":[126],"structures,":[127],"basis":[130],"When":[134],"combined":[135],"optimization":[137],"techniques,":[138],"these":[139],"networks":[140],"mimic":[141],"behaviour":[143],"neurons":[145],"human":[148],"brain":[149],"allow":[151],"computer":[153],"learn":[155],"experiences.":[158],"Here":[159],"we":[160,182],"explore":[161],"one":[162],"many":[164],"potential":[165],"uses":[166],"for":[167],"such":[168],"structures":[169],"-":[170],"analysis":[172],"vocal":[174],"performance":[175],"original":[178],"study.":[179],"In":[180],"particular,":[181],"dissect":[183],"recognition":[185],"systems":[186],"determine":[188],"inner":[190],"workings.":[191]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-12-22T00:00:00"}
