{"id":"https://openalex.org/W4386025412","doi":"https://doi.org/10.1145/3606193.3606201","title":"Speech Recognition Method Based on Deep Learning of Artificial Intelligence","display_name":"Speech Recognition Method Based on Deep Learning of Artificial Intelligence","publication_year":2023,"publication_date":"2023-03-24","ids":{"openalex":"https://openalex.org/W4386025412","doi":"https://doi.org/10.1145/3606193.3606201"},"language":"en","primary_location":{"id":"doi:10.1145/3606193.3606201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606193.3606201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 5th International Symposium on Signal Processing Systems (SSPS)","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/A5101948909","display_name":"Kangyu Chen","orcid":"https://orcid.org/0009-0006-7631-4278"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kangyu Chen","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0006-7631-4278","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107224941","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0009-0003-6560-733X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0003-6560-733X","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9832000136375427,"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/T10860","display_name":"Speech and Audio Processing","score":0.9370999932289124,"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":0.8078963756561279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7385819554328918},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7014409303665161},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5311272144317627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49063363671302795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4364737868309021},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41889840364456177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078963756561279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7385819554328918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7014409303665161},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5311272144317627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49063363671302795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4364737868309021},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41889840364456177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3606193.3606201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606193.3606201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 5th International Symposium on Signal Processing Systems (SSPS)","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":6,"referenced_works":["https://openalex.org/W1993882792","https://openalex.org/W2131774270","https://openalex.org/W2147768505","https://openalex.org/W2916681395","https://openalex.org/W2964170943","https://openalex.org/W4205263358"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1769849273","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536"],"abstract_inverted_index":{"Under":[0],"the":[1,41,55,67,70,89,103,117,123,134,143,150,160,175,178,183,187,202],"influence":[2],"of":[3,26,43,57,74,92,128,136,146,153],"information,":[4],"network":[5],"and":[6,14,21,34,45,61,72,80,139,149,180],"intelligent":[7,12,77,81,93],"high-speed":[8],"development":[9,42],"situation,":[10],"China's":[11],"technology":[13,33,60,79],"other":[15],"aspects":[16],"have":[17],"made":[18],"great":[19],"progress":[20],"achievements,":[22],"derived":[23],"a":[24,194],"lot":[25],"advanced":[27],"artificial":[28,58,75],"intelligence":[29,44,51,59],"technology,":[30,37,64,96],"machine":[31,62],"learning":[32,36,53,63,162],"deep":[35,52,110,161],"etc.,":[38],"to":[39,87,100,116],"promote":[40],"information":[46],"in":[47,85,165],"major":[48],"fields.":[49],"Artificial":[50],"is":[54,98],"fusion":[56],"which":[65],"lays":[66],"foundation":[68],"for":[69],"reform":[71],"innovation":[73],"voice":[76],"recognition":[78,95,105,191,196,205],"robot":[82],"technology.":[83],"So":[84],"order":[86],"improve":[88],"application":[90],"level":[91],"speech":[94,104,137,147,190,204],"it":[97],"necessary":[99],"continuously":[101],"optimize":[102],"method":[106],"based":[107,158],"on":[108,159,177],"AI":[109],"learning.":[111],"In":[112],"this":[113,120,166],"regard,":[114],"according":[115],"relevant":[118],"literature,":[119],"paper":[121,167],"addresses":[122],"problem":[124],"that":[125,186],"phoneme":[126,151],"features":[127,141,152],"varying":[129],"duration":[130],"are":[131,156],"generated":[132],"during":[133],"propagation":[135],"signals,":[138],"these":[140],"affect":[142],"correct":[144],"rate":[145,199],"recognition,":[148],"different":[154],"lengths":[155],"standardized":[157],"research":[163],"mentioned":[164],"with":[168,201],"BLSTM-CTC":[169,189],"as":[170],"an":[171],"example.":[172],"By":[173],"evaluating":[174],"model":[176,192],"Thchs30":[179],"ST-CMDS":[181],"datasets,":[182],"results":[184],"show":[185],"MCFN-based":[188],"has":[193],"reduced":[195],"word":[197],"error":[198],"compared":[200],"traditional":[203],"model.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}