{"id":"https://openalex.org/W4400268602","doi":"https://doi.org/10.1145/3665348.3665366","title":"Research on acoustic Model of Putian Dialect Speech Recognition Based on Deep Learning","display_name":"Research on acoustic Model of Putian Dialect Speech Recognition Based on Deep Learning","publication_year":2024,"publication_date":"2024-05-10","ids":{"openalex":"https://openalex.org/W4400268602","doi":"https://doi.org/10.1145/3665348.3665366"},"language":"en","primary_location":{"id":"doi:10.1145/3665348.3665366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665348.3665366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Generative Artificial Intelligence and Information Security","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084197929","display_name":"Huilin Fang","orcid":"https://orcid.org/0009-0002-0308-410X"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilin Fang","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University, China"],"raw_orcid":"https://orcid.org/0009-0002-0308-410X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University, China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037682721","display_name":"Zhiguo Zhou","orcid":"https://orcid.org/0009-0005-6145-6268"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguo Zhou","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University, China"],"raw_orcid":"https://orcid.org/0009-0005-6145-6268","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University, China","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184983240"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07868204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919999837875366,"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":0.9919999837875366,"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":0.911899983882904,"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/speech-recognition","display_name":"Speech recognition","score":0.7029378414154053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696013808250427},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4538012146949768},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4290691018104553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4285619854927063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4259183704853058}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029378414154053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696013808250427},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4538012146949768},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4290691018104553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4285619854927063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4259183704853058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3665348.3665366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665348.3665366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Generative Artificial Intelligence and Information Security","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2080562691","https://openalex.org/W4384928248","https://openalex.org/W6752456723"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2136763963","https://openalex.org/W3215138031","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W1909151225","https://openalex.org/W1987783679"],"abstract_inverted_index":{"The":[0],"Putian":[1,30,54,86,101,164],"dialect":[2,31,55,102,165],"is":[3,16,39],"an":[4,43,148],"ancient":[5],"language":[6],"with":[7,136],"a":[8,17,80,137,157],"rich":[9],"historical":[10],"and":[11,125,175],"cultural":[12],"background.":[13],"Currently,":[14],"there":[15],"lack":[18],"of":[19,42,53,60,141,151],"published":[20],"research":[21],"on":[22,89],"automatic":[23],"speech":[24,97],"recognition":[25,98],"(ASR)":[26],"technology":[27],"for":[28,47,99,161],"the":[29,40,51,85,100,129,133],"due":[32],"to":[33,70,84,95,155,184],"various":[34,104],"reasons.":[35],"One":[36],"notable":[37],"example":[38],"absence":[41],"audio":[44],"corpus":[45,82],"specifically":[46],"this":[48,90,144],"dialect.":[49,87],"Moreover,":[50],"pronunciation":[52],"significantly":[56],"differs":[57],"from":[58,79],"that":[59],"Mandarin":[61,167],"used":[62],"in":[63,153],"our":[64],"daily":[65],"lives.":[66],"This":[67,169],"paper":[68],"aims":[69],"address":[71],"these":[72],"challenges":[73],"by":[74,180],"collecting":[75],"8000":[76],"isolated":[77],"words":[78],"phonetic":[81],"dedicated":[83],"Based":[88],"self-built":[91],"database,":[92],"I":[93,146],"attempt":[94],"achieve":[96],"using":[103,185],"models":[105],"such":[106],"as":[107],"single":[108],"phoneme":[109,162],"model":[110,124,131],"recognition,":[111],"three-phoneme":[112],"model,":[113],"linear":[114],"discriminant":[115],"analysis,":[116],"maximum":[117],"likelihood":[118],"change,":[119],"speaker":[120],"adaptive":[121],"training,":[122],"quick":[123],"DNN-HMM":[126],"model.":[127],"Notably,":[128],"DNN-HMM-2":[130],"yields":[132],"best":[134],"results":[135],"word":[138],"error":[139,178],"rate":[140,179],"20.56%.":[142],"In":[143],"experiment,":[145],"introduce":[147],"additional":[149],"layer":[150],"mapping":[152,159],"order":[154],"construct":[156],"two-step":[158],"method":[160],"-":[163,166],"alignment.":[168],"approach":[170],"improves":[171],"training":[172],"alignment":[173],"accuracy":[174],"reduces":[176],"character":[177],"approximately":[181],"3%":[182],"compared":[183],"only":[186],"one-level":[187],"mapping.":[188]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}