{"id":"https://openalex.org/W4405709203","doi":"https://doi.org/10.1109/iscslp63861.2024.10799993","title":"CMAST: Efficient Speech-Text Joint Training Method to Enhance Linguistic Features Learning of Speech Representations","display_name":"CMAST: Efficient Speech-Text Joint Training Method to Enhance Linguistic Features Learning of Speech Representations","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709203","doi":"https://doi.org/10.1109/iscslp63861.2024.10799993"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10799993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5055370974","display_name":"Jingran Xie","orcid":"https://orcid.org/0009-0007-2050-263X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingran Xie","raw_affiliation_strings":["Pengcheng Laboratory,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Shenzhen","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020605377","display_name":"Changhe Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhe Song","raw_affiliation_strings":["Pengcheng Laboratory,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Shenzhen","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632572","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0003-1395-6805"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Pengcheng Laboratory,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Shenzhen","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731006","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-0499-727X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Pengcheng Laboratory,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,Shenzhen","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5055370974"],"corresponding_institution_ids":["https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21950669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"656","last_page":"660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9855999946594238,"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":0.9855999946594238,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9553999900817871,"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/T12031","display_name":"Speech and dialogue systems","score":0.9140999913215637,"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":0.8001566529273987},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6841211915016174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6176432371139526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5537571907043457},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5523397326469421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027384757995605},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4456103444099426},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44265109300613403},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4203776717185974},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07566797733306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001566529273987},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6841211915016174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6176432371139526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5537571907043457},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5523397326469421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027384757995605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4456103444099426},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44265109300613403},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4203776717185974},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07566797733306885},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10799993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2118020555","https://openalex.org/W2619383789","https://openalex.org/W2972943112","https://openalex.org/W3197580070","https://openalex.org/W3198299542","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226120743","https://openalex.org/W4287890956","https://openalex.org/W4385245566","https://openalex.org/W4385573012","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6767737316","https://openalex.org/W6780218876","https://openalex.org/W6786669483","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6791904447","https://openalex.org/W6803092890","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"Self-supervised":[0],"pre-training":[1],"on":[2,32,95,121],"speech":[3,15,41,65,76,118],"modality":[4],"has":[5],"exhibited":[6],"promising":[7],"performance":[8,115,140],"in":[9,27],"diverse":[10],"domains.":[11],"However,":[12],"self-supervised":[13],"learned":[14],"representations":[16],"often":[17],"fail":[18],"to":[19,57,84,99,129],"sufficiently":[20],"highlight":[21],"linguistic":[22,33,86],"content,":[23],"limiting":[24],"their":[25],"effectiveness":[26,102],"situations":[28],"that":[29,109],"rely":[30],"heavily":[31],"information,":[34],"such":[35],"as":[36,58],"intent":[37],"classification":[38],"and":[39,66,77,145],"automatic":[40],"recognition":[42],"tasks.":[43,126],"To":[44],"address":[45],"this":[46],"limitation,":[47],"we":[48],"introduce":[49],"an":[50],"efficient":[51],"speech-text":[52,131],"joint":[53,132],"training":[54,147],"method,":[55],"referred":[56],"CMAST,":[59],"which":[60],"leverages":[61],"cross-modal":[62],"alignment":[63],"between":[64],"text":[67,78],"pre-trained":[68,81,119,133],"models.":[69],"With":[70],"a":[71,122],"limited":[72],"amount":[73],"of":[74,103,124],"paired":[75],"data,":[79],"the":[80,96,101],"model's":[82],"ability":[83],"capture":[85],"content":[87],"is":[88],"significantly":[89],"enhanced.":[90],"We":[91],"conduct":[92],"extensive":[93],"evaluations":[94],"SUPERB":[97],"platform":[98],"verify":[100],"our":[104,110,135],"approach.":[105],"The":[106],"results":[107],"show":[108],"CMAST":[111,136],"model":[112,137],"achieves":[113],"superior":[114],"over":[116],"previous":[117],"models":[120],"series":[123],"downstream":[125],"In":[127],"contrast":[128],"state-of-the-art":[130],"models,":[134],"presents":[138],"comparable":[139],"while":[141],"requiring":[142],"fewer":[143],"parameters":[144],"less":[146],"data.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}