{"id":"https://openalex.org/W4327521189","doi":"https://doi.org/10.1145/3573428.3573659","title":"Analyzing speaker information in self-supervised models to improve unsupervised speech recognition","display_name":"Analyzing speaker information in self-supervised models to improve unsupervised speech recognition","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4327521189","doi":"https://doi.org/10.1145/3573428.3573659"},"language":"en","primary_location":{"id":"doi:10.1145/3573428.3573659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573659","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","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/A5027491830","display_name":"Sirui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sirui Li","raw_affiliation_strings":["Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074375399","display_name":"Qinya Zhang","orcid":"https://orcid.org/0000-0002-6420-6062"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinya Zhang","raw_affiliation_strings":["Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055369187","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4217-890X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012696718","display_name":"Guanyu Li","orcid":"https://orcid.org/0000-0001-9639-5825"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Li","raw_affiliation_strings":["Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069875092","display_name":"Senyan Li","orcid":"https://orcid.org/0000-0002-5556-4167"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senyan Li","raw_affiliation_strings":["Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002416122","display_name":"Shaoxuan Wang","orcid":"https://orcid.org/0000-0003-2565-9971"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxuan Wang","raw_affiliation_strings":["Conservatory of Music, Northwest Minzu University, China"],"affiliations":[{"raw_affiliation_string":"Conservatory of Music, Northwest Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027491830"],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18146429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1300","last_page":"1305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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":0.986299991607666,"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":0.9811000227928162,"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":0.8094156384468079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7607725262641907},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7133204340934753},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6672876477241516},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6397488117218018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5885785222053528},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5301901698112488},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4867672920227051},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4460073709487915},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42772677540779114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40012016892433167},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3355143666267395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8094156384468079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7607725262641907},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7133204340934753},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6672876477241516},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6397488117218018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5885785222053528},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5301901698112488},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4867672920227051},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4460073709487915},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42772677540779114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40012016892433167},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3355143666267395},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573428.3573659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573659","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1981276685","https://openalex.org/W2468716020","https://openalex.org/W2998702515","https://openalex.org/W3098643042","https://openalex.org/W4212807739","https://openalex.org/W6600223117","https://openalex.org/W6603308362","https://openalex.org/W6603795164","https://openalex.org/W6605866443","https://openalex.org/W6630334170","https://openalex.org/W6698701979"],"related_works":["https://openalex.org/W2140022733","https://openalex.org/W1521049138","https://openalex.org/W1851196109","https://openalex.org/W159433267","https://openalex.org/W1499982184","https://openalex.org/W2982364454","https://openalex.org/W2055842011","https://openalex.org/W2071925552","https://openalex.org/W2295657453","https://openalex.org/W2019395288"],"abstract_inverted_index":{"The":[0,86],"quality":[1],"of":[2,11,20,45,77,83,127],"speech":[3,13,34,47,88,104,129],"representation":[4,82],"is":[5,27],"the":[6,9,43,58,74,102,112,117,124],"key":[7],"to":[8,33,94,98],"success":[10],"unsupervised":[12,46,103,128],"recognition.":[14,48,130],"Self-supervised":[15],"models":[16],"contain":[17],"a":[18,81],"variety":[19],"audio":[21,59],"information,":[22,53],"and":[23,65,70,72],"non-speech":[24],"content":[25],"information":[26,39],"not":[28],"beneficial":[29],"or":[30],"even":[31],"harmful":[32],"recognition,":[35],"so":[36],"removing":[37],"speaker":[38,52,84,92,118],"can":[40,121],"greatly":[41],"improve":[42],"accuracy":[44],"To":[49],"effectively":[50],"remove":[51],"this":[54],"paper":[55],"first":[56],"analyzes":[57],"features":[60,97],"extracted":[61,87],"by":[62],"wav2vec":[63],"2.0":[64],"HuBERT":[66],"self-supervised":[67],"model":[68,106],"qualitatively":[69],"quantitatively,":[71],"derives":[73],"mean":[75],"value":[76],"each":[78],"sentence":[79],"as":[80],"information.":[85],"representations":[89],"are":[90],"then":[91],"normalized":[93],"obtain":[95],"valid":[96],"be":[99],"fed":[100],"into":[101],"recognition":[105],"for":[107],"training.":[108],"Experimental":[109],"results":[110],"on":[111],"TIMIT":[113],"dataset":[114],"show":[115],"that":[116],"normalization":[119],"method":[120],"significantly":[122],"reduce":[123],"error":[125],"rate":[126]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}