{"id":"https://openalex.org/W4225534571","doi":"https://doi.org/10.21437/interspeech.2022-10796","title":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","display_name":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225534571","doi":"https://doi.org/10.21437/interspeech.2022-10796"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10796","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10796","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5024324721","display_name":"Dan Berrebbi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dan Berrebbi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125256","display_name":"Brian Yan","orcid":"https://orcid.org/0000-0002-4160-6282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051853293","display_name":"Osbel L\u00f3pez-Francisco","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osbel L\u00f3pez-Francisco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113468033","display_name":"Jonathan D. Amith","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Amith","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024324721"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5647,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84838368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3533","last_page":"3537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.991599977016449,"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":0.982699990272522,"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":0.8012208938598633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.59639573097229},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5712037682533264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5642436146736145},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5511425137519836},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5120037198066711},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5098564028739929},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.490771621465683},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48552751541137695},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4390980303287506},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4208322763442993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39570531249046326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3715580701828003},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09995594620704651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012208938598633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59639573097229},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5712037682533264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5642436146736145},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5511425137519836},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5120037198066711},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5098564028739929},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.490771621465683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48552751541137695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4390980303287506},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4208322763442993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39570531249046326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3715580701828003},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09995594620704651},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10796","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10796","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4287241967","https://openalex.org/W3144173820","https://openalex.org/W4317548404","https://openalex.org/W3022007134","https://openalex.org/W2130553454","https://openalex.org/W2033364610"],"abstract_inverted_index":{"Self-Supervised":[0],"Learning":[1],"(SSL)":[2],"models":[3,79,111,147],"have":[4],"been":[5],"successfully":[6],"applied":[7],"in":[8,155],"various":[9],"deep":[10],"learning-based":[11],"speech":[12,87],"tasks,":[13],"particularly":[14],"those":[15],"with":[16],"a":[17,91,130],"limited":[18],"amount":[19],"of":[20,25,132,145,157],"data.":[21,168],"However,":[22],"the":[23,31,34,39,44,70,142,165],"quality":[24],"SSL":[26,35,78,100,110,146,161],"representations":[27],"depends":[28],"highly":[29],"on":[30,112,122],"relatedness":[32],"between":[33,160],"training":[36,162],"domain(s)":[37],"and":[38,58,93,99,109,117,164],"target":[40,166],"data":[41],"domain.":[42],"On":[43],"contrary,":[45],"spectral":[46],"feature":[47],"(SF)":[48],"extractors":[49,76,151],"such":[50],"as":[51],"log":[52],"Mel-filterbanks":[53],"are":[54],"hand-crafted":[55],"non-learnable":[56,74],"components,":[57],"could":[59],"be":[60],"more":[61],"robust":[62],"to":[63,77,84,96],"domain":[64,158],"shifts.":[65],"The":[66,102],"present":[67],"work":[68],"examines":[69],"assumption":[71],"that":[72,141],"combining":[73],"SF":[75,98,150],"is":[80,152],"an":[81],"effective":[82],"approach":[83],"low":[85,124],"resource":[86,125],"tasks.":[88],"We":[89,127],"propose":[90],"learnable":[92],"interpretable":[94],"framework":[95,104],"combine":[97],"representations.":[101],"proposed":[103],"outperforms":[105],"significantly":[106],"both":[107],"baseline":[108],"Automatic":[113],"Speech":[114,118],"Recognition":[115],"(ASR)":[116],"Translation":[119],"(ST)":[120],"tasks":[121],"three":[123],"datasets.":[126],"additionally":[128],"design":[129],"mixture":[131],"experts":[133],"based":[134],"combination":[135],"model.":[136],"This":[137],"last":[138],"model":[139],"reveals":[140],"relative":[143],"contribution":[144],"over":[148],"conventional":[149],"very":[153],"small":[154],"case":[156],"mismatch":[159],"set":[163],"language":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}