{"id":"https://openalex.org/W7125944563","doi":"https://doi.org/10.1109/sdpc68151.2025.11347818","title":"Real-Time Speech Transcription and Spoken Speech Speed Detection Synchronized Subtitle Delivery Algorithm","display_name":"Real-Time Speech Transcription and Spoken Speech Speed Detection Synchronized Subtitle Delivery Algorithm","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W7125944563","doi":"https://doi.org/10.1109/sdpc68151.2025.11347818"},"language":"en","primary_location":{"id":"doi:10.1109/sdpc68151.2025.11347818","doi":"https://doi.org/10.1109/sdpc68151.2025.11347818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sdpc68151.2025.11347818","pdf_url":null,"source":{"id":"https://openalex.org/S4306498546","display_name":"International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5124149065","display_name":"Xiaoman Mo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405280034","display_name":"Zhongshan Torch Polytechnic","ror":"https://ror.org/02b76ce64","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoman Mo","raw_affiliation_strings":["Zhongshan Torch Polytechnic,Zhongshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongshan Torch Polytechnic,Zhongshan,China","institution_ids":["https://openalex.org/I4405280034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030388399","display_name":"Imelda M. Flores","orcid":"https://orcid.org/0000-0001-8940-894X","observed_orcids":["https://orcid.org/0000-0001-8940-894X"]},"institutions":[{"id":"https://openalex.org/I3516337","display_name":"Batangas State University","ror":"https://ror.org/019en2y21","country_code":"PH","type":"education","lineage":["https://openalex.org/I3516337"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Imelda M. Flores","raw_affiliation_strings":["Batangas State University,College of Teacher Education,Batangas City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Batangas State University,College of Teacher Education,Batangas City,Philippines","institution_ids":["https://openalex.org/I3516337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9897000193595886,"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":0.9897000193595886,"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":0.009200000204145908,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.8040000200271606},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"dynamic time warping","score":0.9570000171661377},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.9520000219345093}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.7250000238418579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150999903678894},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6894000172615051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6624000072479248},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sdpc68151.2025.11347818","doi":"https://doi.org/10.1109/sdpc68151.2025.11347818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sdpc68151.2025.11347818","pdf_url":null,"source":{"id":"https://openalex.org/S4306498546","display_name":"International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385478271","https://openalex.org/W7219035982","https://openalex.org/W2123924326","https://openalex.org/W3126192030","https://openalex.org/W2523760423","https://openalex.org/W80640639","https://openalex.org/W2084814098","https://openalex.org/W4411727076","https://openalex.org/W49921992","https://openalex.org/W7196945270"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,84,97,126,136,145,159,174,181],"bottleneck":[3],"of":[4,69,90,155,167,176,184],"insufficient":[5],"coordination":[6],"between":[7],"speech":[8,10,25,29,42,47,59,94,123],"transcription,":[9],"speed":[11,30,48,133],"detection,":[12,125],"and":[13,27,54,57,79,106,135,158,179],"subtitle":[14,18,33,61,143,186],"delivery":[15,34,62],"in":[16],"real-time":[17,24,185],"technology,":[19],"this":[20],"paper":[21],"proposes":[22],"a":[23,39,45,58,66,88,100,107,151,164],"transcription":[26,43,95,114],"spoken":[28],"detection":[31,49,138],"synchronized":[32],"algorithm.":[35],"This":[36,170],"algorithm":[37,86,171],"constructs":[38],"multimodal":[40],"fusion":[41],"module,":[44],"two-stage":[46],"module":[50],"based":[51,73],"on":[52,74,96],"DTW":[53],"attention":[55],"mechanisms,":[56],"speed-adaptive":[60],"scheduling":[63],"model,":[64],"forming":[65],"four-layer":[67],"architecture":[68],"\"perception-analysis-decision-":[70],"decision-delivery.\"":[71],"Experiments":[72],"three":[75],"datasets":[76],"(AISHELL-3,":[77],"LibriSpeech,":[78],"mixed-scenario":[80,98],"data)":[81],"show":[82],"that":[83],"proposed":[85],"achieves":[87],"WER":[89],"only":[91],"7.5%":[92],"for":[93],"dataset,":[99],"33.0%":[101],"reduction":[102,109],"compared":[103,110],"to":[104,111],"LSTM-CTC":[105],"19.4%":[108],"Transformer-ASR.":[112],"The":[113],"latency":[115],"remains":[116,162],"stable":[117],"at":[118],"less":[119],"than":[120],"92ms.":[121],"For":[122,142],"rate":[124],"MAE":[127],"is":[128,140,148],"\u22642.5":[129],"words/minute":[130],"across":[131],"all":[132],"ranges,":[134],"mutation":[137],"accuracy":[139],"\u226589.5%.":[141],"push,":[144],"synchronization":[146],"error":[147],"\u226431ms,":[149],"with":[150],"subjective":[152],"satisfaction":[153],"rating":[154],"8.7":[156],"points,":[157],"text":[160],"density":[161],"within":[163],"reasonable":[165],"range":[166],"1.5-3.5":[168],"words/second.":[169],"effectively":[172],"overcomes":[173],"limitations":[175],"existing":[177],"technologies":[178],"improves":[180],"overall":[182],"performance":[183],"systems.":[187]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-01-29T00:00:00"}