{"id":"https://openalex.org/W4402980127","doi":"https://doi.org/10.1109/icme57554.2024.10687681","title":"SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition","display_name":"SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980127","doi":"https://doi.org/10.1109/icme57554.2024.10687681"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687681","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5014632942","display_name":"Hongfei Xue","orcid":"https://orcid.org/0000-0001-9691-9668"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Xue","raw_affiliation_strings":["Northwestern Polytechnical University,School of Software,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Software,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018773485","display_name":"Qijie Shao","orcid":"https://orcid.org/0009-0000-2145-4077"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijie Shao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608028","display_name":"Kaixun Huang","orcid":"https://orcid.org/0000-0001-7498-4397"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixun Huang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Software,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Software,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085355820","display_name":"Peikun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peikun Chen","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454179","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-0895-7598"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["HuaWei Cloud HuaWei,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HuaWei Cloud HuaWei,Xi’an,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55858136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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":0.9936000108718872,"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":0.9605000019073486,"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":0.7964574694633484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6785235404968262},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5689313411712646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996335506439209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964574694633484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6785235404968262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5689313411712646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996335506439209}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687681","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multilingual":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"systems":[5],"have":[6,24],"garnered":[7],"attention":[8],"for":[9],"their":[10,26],"potential":[11],"to":[12,63,157],"extend":[13],"language":[14,112],"coverage":[15],"globally.":[16],"While":[17],"self-supervised":[18,59],"learning":[19],"(SSL)":[20],"models,":[21],"like":[22],"MMS,":[23],"demonstrated":[25],"effectiveness":[27],"in":[28,95,127],"multilingual":[29,140],"ASR,":[30],"it":[31],"is":[32],"worth":[33],"noting":[34],"that":[35,43,57,78,151],"various":[36],"layers\u2019":[37],"representations":[38,61],"potentially":[39],"contain":[40],"distinct":[41],"information":[42,126],"has":[44],"not":[45],"been":[46],"fully":[47],"leveraged.":[48],"In":[49],"this":[50],"study,":[51],"we":[52,100,118],"propose":[53],"a":[54,102],"novel":[55],"method":[56,153],"leverages":[58],"hierarchical":[60],"(SSHR)":[62],"fine-tune":[64],"the":[65,71,79,86,96,120,128,147,158],"MMS":[66,75],"model.":[67],"We":[68,135],"first":[69],"analyze":[70],"different":[72],"layers":[73,81,88,108,130],"of":[74,160],"and":[76,85,109,144,146],"show":[77],"middle":[80,107],"capture":[82],"language-related":[83,103],"information,":[84,91],"high":[87],"encode":[89],"content-related":[90,125],"which":[92],"gradually":[93],"decreases":[94],"final":[97,129],"layers.":[98],"Then,":[99],"extract":[101],"frame":[104],"from":[105],"correlated":[106],"guide":[110],"specific":[111],"extraction":[113],"through":[114],"self-attention":[115],"mechanisms.":[116],"Additionally,":[117],"steer":[119],"model":[121],"toward":[122],"acquiring":[123],"more":[124],"using":[131],"our":[132,152,161],"proposed":[133],"Cross-CTC.":[134],"evaluate":[136],"SSHR":[137],"on":[138],"two":[139],"datasets,":[141],"Common":[142],"Voice":[143],"ML-SUPERB,":[145],"experimental":[148],"results":[149],"demonstrate":[150],"achieves":[154],"state-of-the-art":[155],"performance":[156],"best":[159],"knowledge.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}