{"id":"https://openalex.org/W4224920362","doi":"https://doi.org/10.1109/icassp43922.2022.9747573","title":"Neural-FST Class Language Model for End-to-End Speech Recognition","display_name":"Neural-FST Class Language Model for End-to-End Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920362","doi":"https://doi.org/10.1109/icassp43922.2022.9747573"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5091201956","display_name":"Antoine Bruguier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antoine Bruguier","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048148168","display_name":"Dangna Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dangna Li","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462347","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-8578-2635"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101666877","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-4557-9429"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022139342","display_name":"Eun Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eun Chang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047400593","display_name":"Fuchun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuchun Peng","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.3114,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48046647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"6107","last_page":"6111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.7764143943786621},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7502421140670776},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6368018388748169},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.597367525100708},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5417656302452087},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.49451157450675964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48498058319091797},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4786035716533661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4506223797798157},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43421927094459534},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3381597399711609},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09493017196655273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764143943786621},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7502421140670776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6368018388748169},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.597367525100708},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5417656302452087},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49451157450675964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48498058319091797},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4786035716533661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4506223797798157},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43421927094459534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3381597399711609},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09493017196655273},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494464848","https://openalex.org/W1505369858","https://openalex.org/W1604697534","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2109831181","https://openalex.org/W2121227244","https://openalex.org/W2137644731","https://openalex.org/W2171928131","https://openalex.org/W2406494896","https://openalex.org/W2749648329","https://openalex.org/W2888779557","https://openalex.org/W2891628540","https://openalex.org/W2938947737","https://openalex.org/W2962760690","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963979492","https://openalex.org/W2972625221","https://openalex.org/W2998704965","https://openalex.org/W3007528493","https://openalex.org/W3008181812","https://openalex.org/W3008480565","https://openalex.org/W3015919780","https://openalex.org/W3016234571","https://openalex.org/W3097239815","https://openalex.org/W3140235797","https://openalex.org/W3149509723","https://openalex.org/W3162665866","https://openalex.org/W3198004110","https://openalex.org/W4293718192","https://openalex.org/W4302339081","https://openalex.org/W6629344606","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6676266797","https://openalex.org/W6678277124","https://openalex.org/W6680532216","https://openalex.org/W6732520560"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2523799048"],"abstract_inverted_index":{"We":[0,75],"propose":[1],"Neural-FST":[2],"Class":[3],"Language":[4],"Model":[5],"(NFCLM)":[6],"for":[7,117],"end-to-end":[8],"speech":[9],"recognition,":[10],"a":[11,27,34,44,59,70],"novel":[12],"method":[13,32],"that":[14,77],"combines":[15],"neural":[16,73],"network":[17],"language":[18],"models":[19,38],"(NNLMs)":[20],"and":[21,98,108],"finite":[22],"state":[23],"transducers":[24],"(FSTs)":[25],"in":[26,85],"mathematically":[28],"consistent":[29],"framework.":[30],"Our":[31],"utilizes":[33],"background":[35,40],"NNLM":[36,81,97],"which":[37],"generic":[39],"text":[41],"together":[42],"with":[43,69],"collection":[45],"of":[46,61,87],"domain-specific":[47],"entities":[48],"modeled":[49],"as":[50,95],"individual":[51],"FSTs.":[52],"Each":[53],"output":[54],"token":[55],"is":[56],"generated":[57],"by":[58,82],"mixture":[60,65],"these":[62],"components;":[63],"the":[64],"weights":[66],"are":[67],"estimated":[68],"separately":[71],"trained":[72],"decider.":[74],"show":[76],"NFCLM":[78,91],"significantly":[79],"outperforms":[80],"15.8%":[83],"relative":[84],"terms":[86],"Word":[88],"Error":[89],"Rate.":[90],"achieves":[92],"similar":[93],"performance":[94],"traditional":[96],"FST":[99],"shallow":[100],"fusion":[101],"while":[102],"being":[103],"less":[104],"prone":[105],"to":[106],"overbiasing":[107],"12":[109],"times":[110],"more":[111,115],"compact,":[112],"making":[113],"it":[114],"suitable":[116],"on-device":[118],"usage.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}