{"id":"https://openalex.org/W7130611000","doi":"https://doi.org/10.1109/apccas67402.2025.11373922","title":"Implementation and Analysis of Mandarin Lipreading on Edge Devices","display_name":"Implementation and Analysis of Mandarin Lipreading on Edge Devices","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7130611000","doi":"https://doi.org/10.1109/apccas67402.2025.11373922"},"language":null,"primary_location":{"id":"doi:10.1109/apccas67402.2025.11373922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11373922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5087997668","display_name":"Yu-Hsuan Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsuan Tseng","raw_affiliation_strings":["Institute of Artificial Intelligence, Crossdisciplinary Technology National Taiwan University of Science and Technology,Department of Graduate,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Crossdisciplinary Technology National Taiwan University of Science and Technology,Department of Graduate,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126419180","display_name":"Che-Min Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Min Tsai","raw_affiliation_strings":["Institute of Artificial Intelligence, Crossdisciplinary Technology National Taiwan University of Science and Technology,Department of Graduate,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Crossdisciplinary Technology National Taiwan University of Science and Technology,Department of Graduate,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065499177","display_name":"Chong-Hao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chong-Hao Xu","raw_affiliation_strings":["National Taiwan University of Science and Technology,Department of Electronic and Computer Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Department of Electronic and Computer Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040147572","display_name":"Shang-Jang Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Jang Ruan","raw_affiliation_strings":["National Taiwan University of Science and Technology,Department of Electronic and Computer Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Department of Electronic and Computer Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.64957308,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5430999994277954,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5430999994277954,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.193900004029274,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.03150000050663948,"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/software-deployment","display_name":"Software deployment","score":0.6815000176429749},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6281999945640564},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6107000112533569},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4440000057220459},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.43630000948905945},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4122999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440000176429749},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6815000176429749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6751999855041504},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.43630000948905945},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2513999938964844},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas67402.2025.11373922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11373922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2898926657","https://openalex.org/W3099231112","https://openalex.org/W4225305629","https://openalex.org/W4229442847","https://openalex.org/W4285201730","https://openalex.org/W4319862233","https://openalex.org/W4399541983","https://openalex.org/W4408977290"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"recognition":[1,74,203],"technology":[2],"is":[3,102,131],"becoming":[4,47],"popular":[5],"in":[6,14,34,97,153],"daily":[7],"life,":[8],"but":[9],"it":[10,78,117],"still":[11],"lacks":[12],"accuracy":[13],"some":[15],"situations":[16],"due":[17],"to":[18],"noise":[19,22],"or":[20,37,140],"environmental":[21],"interference.":[23],"Thus,":[24],"lipreading":[25,52,73,108,202],"methods":[26],"based":[27],"on":[28,63,79,104,205],"visual":[29],"signals":[30],"can":[31,174],"be":[32],"used":[33],"noisy":[35],"environments":[36],"as":[38],"a":[39,71,86,112,126,135,141,201],"communication":[40],"aid":[41],"for":[42,119],"individuals":[43],"with":[44,85,133,178],"hearing":[45],"impairments,":[46],"another":[48],"viable":[49],"option.":[50],"However,":[51],"models":[53],"usually":[54],"involve":[55],"high":[56],"computational":[57],"complexity,":[58],"making":[59,116],"their":[60,166],"real-time":[61,176],"deployment":[62,190],"resourceconstrained":[64],"embedded":[65],"devices":[66,207],"challenging.":[67],"This":[68,194],"study":[69,145,195],"proposes":[70],"Mandarin":[72,107],"model":[75,101,187,204],"and":[76,95,110,130,159,164,183,189,208],"deploys":[77],"an":[80],"edge":[81,206],"computing":[82],"platform":[83,124],"equipped":[84],"commercially":[87],"available":[88],"AI":[89],"accelerator":[90],"evaluating":[91],"the":[92,105,147,150,197,213],"inference":[93,156],"performance":[94],"latency":[96,182],"real-world":[98],"scenarios.":[99],"The":[100,122,144,168],"trained":[103],"DMCLR":[106],"dataset":[109],"uses":[111],"lightweight":[113],"architecture":[114],"design,":[115],"suitable":[118],"resource-constrained":[120],"devices.":[121],"experimental":[123],"utilizes":[125],"Raspberry":[127],"Pi":[128],"5":[129],"tested":[132],"either":[134],"Google":[136],"Coral":[137],"Edge":[138],"TPU":[139],"Hailo-8":[142,179],"accelerator.":[143],"compares":[146],"differences":[148],"between":[149],"two":[151],"accelerators":[152,173],"terms":[154],"of":[155,199,215],"speed,":[157],"accuracy,":[158,185],"temporal":[160],"task":[161],"processing":[162],"capabilities":[163],"analyzes":[165],"limitations.":[167],"results":[169],"show":[170],"that":[171],"both":[172],"support":[175],"inference,":[177],"exhibiting":[180],"lower":[181],"higher":[184],"although":[186],"conversion":[188],"are":[191],"more":[192],"complex.":[193],"demonstrates":[196],"feasibility":[198],"deploying":[200],"provides":[209],"practical":[210],"insights":[211],"into":[212],"selection":[214],"accelerators.":[216]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-20T00:00:00"}