{"id":"https://openalex.org/W4392903327","doi":"https://doi.org/10.1109/icassp48485.2024.10446800","title":"Extending Multilingual ASR to New Languages Using Supplementary Encoder and Decoder Components","display_name":"Extending Multilingual ASR to New Languages Using Supplementary Encoder and Decoder Components","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903327","doi":"https://doi.org/10.1109/icassp48485.2024.10446800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325084","display_name":"Zhipeng Chen","orcid":"https://orcid.org/0000-0002-8330-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhipeng Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057042204","display_name":"Tianfeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianfeng Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001136890","display_name":"Tze Yuang Chong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tze Yuang Chong","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318020","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7824-4839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366029","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0002-5476-5768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10586","last_page":"10590"},"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":0.9986000061035156,"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":0.9983000159263611,"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":0.861458420753479},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.8313255310058594},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5918084979057312},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5730905532836914},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5376841425895691},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5085443258285522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48618072271347046},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4583948850631714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4057823717594147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34504324197769165},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06530961394309998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861458420753479},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8313255310058594},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5918084979057312},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5730905532836914},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5376841425895691},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5085443258285522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48618072271347046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4583948850631714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4057823717594147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34504324197769165},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06530961394309998},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2327501763","https://openalex.org/W2788388592","https://openalex.org/W2964213727","https://openalex.org/W4210463634","https://openalex.org/W4221155340","https://openalex.org/W4225274946","https://openalex.org/W4225295099","https://openalex.org/W4226033575","https://openalex.org/W4293363567","https://openalex.org/W4319862635","https://openalex.org/W4319862642","https://openalex.org/W4323066695","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385822397","https://openalex.org/W6759579507","https://openalex.org/W6802744804","https://openalex.org/W6810259195","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Extending":[0],"multilingual":[1],"automatic":[2],"speech":[3],"recognition":[4],"(mASR)":[5],"systems":[6],"to":[7,55,58,69],"new":[8,46,75],"languages":[9,18,54],"poses":[10],"challenges,":[11],"particularly":[12],"when":[13],"training":[14],"data":[15],"for":[16,45,74,96],"existing":[17,53],"is":[19],"limited":[20],"or":[21],"unavailable.":[22],"To":[23],"tackle":[24],"this":[25],"issue,":[26],"we":[27,36,62],"suggest":[28],"utilizing":[29],"supplementary":[30],"encoder":[31,67],"and":[32,39],"decoder":[33,43],"components.":[34],"Specifically,":[35],"propose":[37],"appending":[38],"fine-tuning":[40],"a":[41],"distinct":[42],"designed":[44],"languages,":[47,76],"while":[48],"preserving":[49],"the":[50,90,93,97],"parameters":[51],"of":[52,92,99],"minimize":[56],"disruption":[57],"their":[59],"performance.":[60,85],"Furthermore,":[61],"advocate":[63],"attaching":[64],"an":[65],"additional":[66],"component":[68],"enhance":[70],"acoustic":[71],"representation":[72],"learning":[73],"resulting":[77],"in":[78,81],"substantial":[79],"improvements":[80],"word":[82],"error":[83],"rate":[84],"Our":[86],"experimental":[87],"findings":[88],"demonstrate":[89],"effectiveness":[91],"proposed":[94],"methods":[95],"task":[98],"extending":[100],"language":[101],"support":[102],"within":[103],"mASR":[104],"systems.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
