{"id":"https://openalex.org/W4408696803","doi":"https://doi.org/10.1109/itsc58415.2024.10919672","title":"A Whisper-Based Dialect Speech Recognition Model for VHF Calls in Waterway Traffic*","display_name":"A Whisper-Based Dialect Speech Recognition Model for VHF Calls in Waterway Traffic*","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408696803","doi":"https://doi.org/10.1109/itsc58415.2024.10919672"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10919672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","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/A5021150267","display_name":"Zechen Li","orcid":"https://orcid.org/0000-0002-6584-7654"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zechen Li","raw_affiliation_strings":["School of automation, Chongqing University,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"School of automation, Chongqing University,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113234534","display_name":"Hai-Shui Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Tu","raw_affiliation_strings":["School of automation, Chongqing University,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"School of automation, Chongqing University,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111174863","display_name":"Min Wang","orcid":"https://orcid.org/0009-0003-7063-1553"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["School of automation, Chongqing University,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"School of automation, Chongqing University,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088250298","display_name":"Yuhui Huang","orcid":"https://orcid.org/0000-0002-8575-7285"},"institutions":[{"id":"https://openalex.org/I4210151975","display_name":"Northwest Institute of Nuclear Technology","ror":"https://ror.org/04svrh266","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210151975"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Huang","raw_affiliation_strings":["Northwest Institute of Nuclear Technology,Shanxi,Xi'an,China,710024"],"affiliations":[{"raw_affiliation_string":"Northwest Institute of Nuclear Technology,Shanxi,Xi'an,China,710024","institution_ids":["https://openalex.org/I4210151975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113952580","display_name":"Shan Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Liang","raw_affiliation_strings":["School of automation, Chongqing University,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"School of automation, Chongqing University,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021150267"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26358856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9426000118255615,"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":0.9426000118255615,"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/computer-science","display_name":"Computer science","score":0.7300783395767212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6231632232666016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300783395767212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6231632232666016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10919672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5851723276","display_name":null,"funder_award_id":"2020-ZD4-040","funder_id":"https://openalex.org/F4320322925","funder_display_name":"Ministry of Transport of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320322925","display_name":"Ministry of Transport of the People's Republic of China","ror":"https://ror.org/031wq1t38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2141892084","https://openalex.org/W2768170151","https://openalex.org/W2790105919","https://openalex.org/W2997181764","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3095057960","https://openalex.org/W3097777922","https://openalex.org/W3101080767","https://openalex.org/W3161950572","https://openalex.org/W3197627016","https://openalex.org/W3216675860","https://openalex.org/W4312531397","https://openalex.org/W6755207826","https://openalex.org/W6771467084","https://openalex.org/W6847363464","https://openalex.org/W6859717518"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Very":[0],"High":[1],"Frequency":[2],"(VHF)":[3],"is":[4,48,137],"the":[5,21,41,69,72,92,111,141,174,177,184,189,193,198],"most":[6],"widely":[7],"used":[8],"means":[9],"of":[10,23,60,71,104,143,176,197],"real-time":[11],"voice":[12,108,169],"communication":[13,94],"and":[14,57,76,121,171],"plays":[15],"an":[16],"extremely":[17],"important":[18],"role":[19],"in":[20,164,180],"field":[22],"water":[24],"transportation.":[25],"Existing":[26],"Automatic":[27],"Speech":[28],"Recognition":[29],"(ASR)":[30],"systems":[31],"often":[32,49],"prioritize":[33],"research":[34],"on":[35],"achieving":[36],"higher":[37],"recognition":[38],"accuracy.":[39],"However,":[40],"speech":[42,118],"captured":[43],"by":[44,51],"ship-borne":[45],"VHF":[46,144],"equipment":[47],"accompanied":[50],"horn":[52],"blasts,":[53],"vessel":[54],"engine":[55],"noise,":[56,61],"other":[58],"types":[59],"leading":[62],"to":[63,90,139],"lack":[64],"significant":[65],"effectiveness.":[66],"Furthermore,":[67],"with":[68,132],"development":[70],"shipping":[73],"industry,":[74],"cross-regional":[75],"cross-national":[77],"voyages":[78],"have":[79],"become":[80],"a":[81,117,123,129,151,159],"trend.":[82],"Single-language":[83],"ASR":[84,154],"models":[85],"are":[86],"no":[87],"longer":[88],"sufficient":[89],"meet":[91],"necessary":[93],"demands":[95],"for":[96,161],"waterway":[97],"traffic.":[98],"After":[99],"gathering":[100],"two":[101],"months'":[102],"worth":[103],"actual":[105],"traffic":[106],"command":[107],"data":[109],"from":[110],"upper":[112],"Yangtze":[113],"River,":[114],"we":[115,127],"created":[116],"annotation":[119],"software":[120],"established":[122],"golden":[124],"dataset.":[125],"Then,":[126],"designed":[128],"pre-processing":[130],"method":[131,190],"adjustable":[133],"aggressive":[134],"mode":[135],"which":[136],"specifically":[138],"address":[140],"characteristics":[142],"signals.":[145],"The":[146],"final":[147],"step":[148],"involves":[149],"fine-tuning":[150],"large-scale":[152],"pre-trained":[153],"model,":[155],"utilizing":[156],"it":[157],"as":[158],"converter":[160],"information":[162],"exchange":[163],"maritime":[165],"communication,":[166],"facilitating":[167],"cross-lingual":[168],"interactions,":[170],"simultaneously":[172],"validating":[173],"effective-ness":[175],"approach":[178],"outlined":[179],"this":[181],"paper.":[182],"Additionally,":[183],"experimental":[185],"results":[186],"demonstrate":[187],"that":[188],"could":[191],"reduce":[192],"hardware":[194],"resource":[195],"consumption":[196],"model.":[199]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}