{"id":"https://openalex.org/W4408353272","doi":"https://doi.org/10.1109/icassp49660.2025.10889216","title":"Continuously Learning New Words in Automatic Speech Recognition","display_name":"Continuously Learning New Words in Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353272","doi":"https://doi.org/10.1109/icassp49660.2025.10889216"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101636465","display_name":"Christian Huber","orcid":"https://orcid.org/0000-0003-4680-2896"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian Huber","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023053982","display_name":"Alexander Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101636465"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01883211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9563000202178955,"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":0.9563000202178955,"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":0.8062724471092224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.711592972278595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5018587112426758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4397609829902649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062724471092224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.711592972278595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5018587112426758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4397609829902649}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W76928536","https://openalex.org/W1561264958","https://openalex.org/W2060277733","https://openalex.org/W2089629691","https://openalex.org/W2105660309","https://openalex.org/W2933138175","https://openalex.org/W2972451902","https://openalex.org/W3001434439","https://openalex.org/W3023953056","https://openalex.org/W3119254916","https://openalex.org/W3173767661","https://openalex.org/W3197674197","https://openalex.org/W3197932033","https://openalex.org/W3198004110","https://openalex.org/W3198094329","https://openalex.org/W4226292626","https://openalex.org/W4286224990","https://openalex.org/W4296070390","https://openalex.org/W4312789614","https://openalex.org/W4385245566","https://openalex.org/W4392173735","https://openalex.org/W6780218876","https://openalex.org/W6796581206"],"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":{"Despite":[0],"recent":[1],"advances,":[2],"Automatic":[3],"Speech":[4],"Recognition":[5],"(ASR)":[6],"systems":[7],"are":[8],"still":[9],"far":[10],"from":[11,66,75],"perfect.":[12],"Typical":[13],"errors":[14],"include":[15],"acronyms,":[16],"named":[17],"entities,":[18],"and":[19],"domain-specific":[20],"special":[21],"words":[22,65,91,135],"for":[23,119],"which":[24],"little":[25],"or":[26],"no":[27],"labeled":[28],"data":[29,95,112],"is":[30,99,117],"available.":[31],"To":[32],"address":[33],"the":[34,48,55,60,67,76,83,108,133,145,149],"problem":[35],"of":[36,50,148],"recognizing":[37],"these":[38],"words,":[39],"we":[40,58,79,128],"propose":[41],"a":[42,51,71],"self-supervised":[43],"continual":[44],"learning":[45,98],"approach:":[46],"Given":[47],"audio":[49],"lecture":[52],"talk":[53],"with":[54,125],"corresponding":[56],"slides,":[57],"bias":[59],"model":[61,74,109],"towards":[62],"decoding":[63],"new":[64,90,134],"slides":[68],"by":[69,102],"using":[70],"memory-enhanced":[72],"ASR":[73],"literature.":[77],"Then,":[78],"perform":[80],"inference":[81],"on":[82,110,132],"talk,":[84],"collecting":[85],"utterances":[86],"that":[87,124],"contain":[88],"detected":[89],"into":[92],"an":[93],"adaptation":[94,104],"set.":[96,113],"Continual":[97],"then":[100],"performed":[101],"training":[103],"weights":[105],"added":[106],"to":[107],"this":[111,126],"The":[114],"whole":[115],"procedure":[116],"iterated":[118],"many":[120],"talks.":[121],"We":[122],"show":[123],"approach,":[127],"obtain":[129],"increasing":[130],"performance":[131,147],"when":[136],"they":[137],"occur":[138],"more":[139],"frequently":[140],"(>80%":[141],"recall)":[142],"while":[143],"preserving":[144],"general":[146],"model.":[150]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}