{"id":"https://openalex.org/W4319779560","doi":"https://doi.org/10.1109/iscslp57327.2022.10037938","title":"Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models","display_name":"Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319779560","doi":"https://doi.org/10.1109/iscslp57327.2022.10037938"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037938","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037938","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th 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/A5100719795","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0002-4871-5334"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Suo","raw_affiliation_strings":["OPPO,Data & AI Engineering System,Beijing,China,100026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO,Data & AI Engineering System,Beijing,China,100026","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102216925","display_name":"Yulong Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulong Wan","raw_affiliation_strings":["OPPO,Data & AI Engineering System,Beijing,China,100026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO,Data & AI Engineering System,Beijing,China,100026","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36315929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"33","issue":null,"first_page":"11","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9979000091552734,"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/word-error-rate","display_name":"Word error rate","score":0.8272914886474609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118984699249268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7337578535079956},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7029605507850647},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6716974973678589},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6228480935096741},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5533711910247803},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5032100081443787},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.49991297721862793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4659149944782257},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4500666856765747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43985825777053833},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28307095170021057},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11716282367706299},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11116483807563782},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09388542175292969}],"concepts":[{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.8272914886474609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118984699249268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7337578535079956},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7029605507850647},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6716974973678589},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6228480935096741},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5533711910247803},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5032100081443787},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.49991297721862793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4659149944782257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4500666856765747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43985825777053833},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28307095170021057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11716282367706299},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11116483807563782},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09388542175292969},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037938","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037938","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2090755665","https://openalex.org/W2122364000","https://openalex.org/W2547875792","https://openalex.org/W2591804103","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2973132572","https://openalex.org/W2998284473","https://openalex.org/W3015877095","https://openalex.org/W3029282897","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3093816530","https://openalex.org/W3113594615","https://openalex.org/W3196485121","https://openalex.org/W3197278374","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W4221145109","https://openalex.org/W4221149170","https://openalex.org/W4322714819","https://openalex.org/W6631362777","https://openalex.org/W6679855610","https://openalex.org/W6680300913","https://openalex.org/W6729448088","https://openalex.org/W6771467084","https://openalex.org/W6778215197","https://openalex.org/W6780218876","https://openalex.org/W6787141514","https://openalex.org/W6809739816","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2126322296","https://openalex.org/W2129812225","https://openalex.org/W2244609359"],"abstract_inverted_index":{"Labeled":[0],"audio":[1,35],"data":[2,36],"is":[3,48,85,102,152],"insufficient":[4],"to":[5,26,52,69,89],"build":[6],"satisfying":[7],"speech":[8,31,99],"recognition":[9,32],"systems":[10],"for":[11],"most":[12],"of":[13,37,45,62,93],"the":[14,17,38,42,59,86,91,106,145],"languages":[15,151],"in":[16,55,73],"world.":[18],"There":[19],"have":[20],"been":[21,67],"some":[22,142],"zero-resource":[23,74,98],"methods":[24,47],"trying":[25],"perform":[27],"phoneme":[28,75,111],"or":[29],"word-level":[30,97],"without":[33],"labeled":[34],"target":[39],"language,":[40],"but":[41],"error":[43,139,147],"rate":[44,140,148],"these":[46],"usually":[49],"too":[50],"high":[51],"be":[53,70],"applied":[54],"real-world":[56],"scenarios.":[57],"Recently,":[58],"representation":[60],"ability":[61],"self-supervise":[63],"pre-trained":[64,107],"models":[65,95,108,128],"has":[66],"found":[68],"extremely":[71],"beneficial":[72],"recognition.":[76,100],"As":[77],"far":[78],"as":[79],"we":[80],"are":[81],"concerned,":[82],"this":[83,131],"paper":[84],"first":[87],"attempt":[88],"extend":[90],"use":[92],"pretrained":[94],"into":[96],"This":[101],"done":[103],"by":[104],"fine-tuning":[105],"on":[109,120,124,141,149],"IPA":[110],"transcriptions":[112],"and":[113,126,144],"decoding":[114],"with":[115],"a":[116],"language":[117],"model":[118],"trained":[119],"extra":[121],"texts.":[122],"Experiments":[123],"Wav2vec2.0":[125],"HuBERT":[127],"show":[129],"that":[130],"method":[132],"can":[133],"achieve":[134],"less":[135],"than":[136],"20%":[137],"word":[138],"languages,":[143],"average":[146],"8":[150],"33.77%.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-02-11T00:00:00"}