{"id":"https://openalex.org/W4406461496","doi":"https://doi.org/10.1109/slt61566.2024.10832321","title":"Fusion Of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition","display_name":"Fusion Of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461496","doi":"https://doi.org/10.1109/slt61566.2024.10832321"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5080162587","display_name":"Shih-Heng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Heng Wang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090229064","display_name":"Chien\u2010Yu Huang","orcid":"https://orcid.org/0009-0008-3346-1870"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Yu Huang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080162587"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71157691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.7596708536148071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6365095376968384},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6174988746643066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5132851600646973},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4467405676841736},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20772024989128113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596708536148071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6365095376968384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6174988746643066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5132851600646973},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4467405676841736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20772024989128113},{"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/slt61566.2024.10832321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2191779130","https://openalex.org/W2962780374","https://openalex.org/W3011926625","https://openalex.org/W3036601975","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4225534571","https://openalex.org/W4225615476","https://openalex.org/W4226033575","https://openalex.org/W4226162428","https://openalex.org/W4230442869","https://openalex.org/W4281492411","https://openalex.org/W4283780157","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385822255","https://openalex.org/W4385822439","https://openalex.org/W4385822683","https://openalex.org/W4385823403","https://openalex.org/W4385970143","https://openalex.org/W4390691978","https://openalex.org/W4390874021","https://openalex.org/W4392224124","https://openalex.org/W4392903159","https://openalex.org/W4392904292","https://openalex.org/W4392904805","https://openalex.org/W4392909068","https://openalex.org/W4392909760","https://openalex.org/W4402111598","https://openalex.org/W4402111789","https://openalex.org/W6631190155","https://openalex.org/W6780218876","https://openalex.org/W6803164887","https://openalex.org/W6810321870","https://openalex.org/W6852909395","https://openalex.org/W6855650468","https://openalex.org/W6857589352","https://openalex.org/W6862581974"],"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/W3204019825"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"models":[3,112],"have":[4],"shown":[5],"exceptional":[6],"capabilities":[7],"across":[8],"various":[9],"speech-processing":[10],"tasks.":[11],"Continuous":[12],"SSL":[13,30,102,111],"representations":[14,56],"are":[15],"effective":[16],"but":[17],"suffer":[18],"from":[19],"high":[20],"computational":[21],"and":[22,38,41,48,113,125,131],"storage":[23,39],"demands.":[24],"On":[25],"the":[26,52,75,82,105,140,144],"other":[27],"hand,":[28],"discrete":[29,55,68,78,93],"representations,":[31,94],"although":[32],"with":[33,139],"degraded":[34],"performance,":[35],"reduce":[36],"transmission":[37],"costs,":[40],"improve":[42],"input":[43],"sequence":[44],"efficiency":[45],"through":[46],"de-duplication":[47],"subword-modeling.":[49],"To":[50],"boost":[51],"performance":[53,84],"of":[54,77,146],"for":[57],"ASR,":[58],"we":[59,90],"introduce":[60],"a":[61,99],"novel":[62],"fusion":[63,71,106],"mechanism":[64,72],"that":[65],"integrates":[66],"two":[67],"representations.":[69],"The":[70],"preserves":[73],"all":[74],"benefits":[76],"representation":[79],"while":[80],"enhancing":[81],"model\u2019s":[83],"by":[85],"integrating":[86],"complementary":[87],"information.":[88],"Additionally,":[89],"explore":[91],"\u201cself-augmented\u201d":[92],"which":[95],"apply":[96],"transformations":[97],"to":[98,129],"single":[100],"continuous":[101],"representation,":[103],"eliminating":[104],"mechanism\u2019s":[107],"dependency":[108],"on":[109,121],"multiple":[110],"further":[114],"decreasing":[115],"its":[116],"inference":[117],"costs.":[118],"Experimental":[119],"results":[120],"benchmarks,":[122],"including":[123],"LibriSpeech":[124],"ML-SUPERB,":[126],"indicate":[127],"up":[128],"19%":[130],"24%":[132],"relative":[133],"character":[134],"error":[135],"rate":[136],"improvement":[137],"compared":[138],"non-fusion":[141],"baseline,":[142],"validating":[143],"effectiveness":[145],"our":[147],"proposed":[148],"methods.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}