{"id":"https://openalex.org/W4402352772","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650855","title":"Human Behavior Modeling in Speech Transcribing Process via Pretrained Speech Recognition Models","display_name":"Human Behavior Modeling in Speech Transcribing Process via Pretrained Speech Recognition Models","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352772","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650855"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650855","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5028029416","display_name":"Bao Thang Ta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bao Thang Ta","raw_affiliation_strings":["Viettel AI,Viettel Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel AI,Viettel Group,Hanoi,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010685497","display_name":"Minh Khang Pham","orcid":"https://orcid.org/0009-0000-9673-6909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minh Khang Pham","raw_affiliation_strings":["Viettel AI,Viettel Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel AI,Viettel Group,Hanoi,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064078570","display_name":"Nhat Minh Le","orcid":"https://orcid.org/0000-0002-2498-9314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nhat Minh Le","raw_affiliation_strings":["Viettel AI,Viettel Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel AI,Viettel Group,Hanoi,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["Viettel AI,Viettel Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Viettel AI,Viettel Group,Hanoi,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028029416"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12949845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9994000196456909,"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":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.7988322973251343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7252392768859863},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6024823784828186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4721807539463043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4526672959327698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988322973251343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7252392768859863},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6024823784828186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4721807539463043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4526672959327698},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650855","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2095629250","https://openalex.org/W2127499922","https://openalex.org/W2135241496","https://openalex.org/W2161482971","https://openalex.org/W2801659857","https://openalex.org/W2888945202","https://openalex.org/W2962898354","https://openalex.org/W2962907457","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3100732527","https://openalex.org/W3160766462","https://openalex.org/W3197813307","https://openalex.org/W4221154745","https://openalex.org/W4281779489","https://openalex.org/W4288071627","https://openalex.org/W4292002651","https://openalex.org/W4312095979","https://openalex.org/W4312944707","https://openalex.org/W4313225742","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,45,92,162],"transcribing":[3,83,104],"speech":[4,12,94,103,148],"plays":[5],"a":[6,66],"critical":[7],"role":[8],"in":[9,101,113],"developing":[10],"automatic":[11],"recognition":[13,95,149],"(ASR)":[14],"systems.":[15],"During":[16],"this":[17,86],"process,":[18],"human":[19,130],"transcribers":[20,57,68,124],"listen":[21],"to":[22,51,59,75,97,118],"spoken":[23],"utterances":[24,48,122,154],"and":[25,53,72,110,136],"convert":[26],"them":[27],"into":[28],"accurately":[29],"written":[30],"texts.":[31],"However,":[32],"our":[33,144],"initial":[34],"investigations":[35],"using":[36],"telephone":[37,142],"conversation":[38],"datasets":[39],"have":[40],"shown":[41],"that":[42,123],"approximately":[43],"40%":[44],"the":[46,81,90,102,108,159,163],"recorded":[47],"are":[49],"challenging":[50],"transcribe":[52],"often":[54],"disregarded":[55],"by":[56,155],"due":[58],"various":[60],"factors,":[61],"such":[62,76],"as":[63],"unintelligibility.":[64],"As":[65],"result,":[67],"waste":[69],"significant":[70],"time":[71,135],"effort":[73],"listening":[74],"utterances,":[77],"significantly":[78],"slowing":[79],"down":[80],"overall":[82],"speed.":[84],"In":[85],"paper,":[87],"we":[88,116],"explore":[89],"potential":[91],"pretrained":[93,147],"models":[96,150],"model":[98],"transcribers\u2019":[99],"behavior":[100],"process.":[105],"By":[106],"leveraging":[107],"knowledge":[109],"insights":[111],"encoded":[112],"these":[114],"models,":[115],"aim":[117],"filter":[119],"out":[120],"problematic":[121],"typically":[125],"disregard":[126],"before":[127],"they":[128],"reach":[129],"transcribers,":[131],"thus":[132],"optimizing":[133],"their":[134],"effort.":[137],"Through":[138],"experiments":[139],"on":[140],"practical":[141],"datasets,":[143],"approach":[145],"utilizing":[146],"successfully":[151],"reduces":[152],"unwanted":[153],"50%":[156],"while":[157],"preserving":[158],"high":[160],"quality":[161],"collected":[164],"dataset.":[165]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}