{"id":"https://openalex.org/W4392903837","doi":"https://doi.org/10.1109/icassp48485.2024.10448012","title":"Enhancing Quantised End-to-End ASR Models Via Personalisation","display_name":"Enhancing Quantised End-to-End ASR Models Via Personalisation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903837","doi":"https://doi.org/10.1109/icassp48485.2024.10448012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448012","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/A5082603285","display_name":"Qiuming Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuming Zhao","raw_affiliation_strings":["Tsinghua University,China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007755497","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0003-3190-497X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["University of Cambridge,United Kingdom","University of Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016903406","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-4222-9968"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083894790","display_name":"Mingxing Xu","orcid":"https://orcid.org/0000-0002-3215-3496"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxing Xu","raw_affiliation_strings":["Tsinghua University,China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Tsinghua University,China","Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12426","last_page":"12430"},"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/T11309","display_name":"Music and Audio Processing","score":0.9923999905586243,"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/T10860","display_name":"Speech and Audio Processing","score":0.9904999732971191,"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":0.7642952799797058},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6072856783866882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5535846948623657},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5453644394874573},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5175649523735046},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.49907660484313965},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48833295702934265},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4828672707080841},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46410879492759705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3737003803253174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3683094382286072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11219918727874756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642952799797058},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6072856783866882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5535846948623657},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5453644394874573},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5175649523735046},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.49907660484313965},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48833295702934265},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4828672707080841},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46410879492759705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3737003803253174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3683094382286072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11219918727874756},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448012","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2048526313","https://openalex.org/W2079623482","https://openalex.org/W2119144962","https://openalex.org/W2239847623","https://openalex.org/W2296483664","https://openalex.org/W2395596777","https://openalex.org/W2398054607","https://openalex.org/W2407299475","https://openalex.org/W2739789140","https://openalex.org/W2952265507","https://openalex.org/W2962780374","https://openalex.org/W2964351684","https://openalex.org/W3015501067","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3094861110","https://openalex.org/W3097522836","https://openalex.org/W3097777922","https://openalex.org/W3097891912","https://openalex.org/W3125118953","https://openalex.org/W3168867926","https://openalex.org/W4221138270","https://openalex.org/W4286909525","https://openalex.org/W4296068588","https://openalex.org/W4297841771","https://openalex.org/W4372259858","https://openalex.org/W4378509449","https://openalex.org/W4385822953","https://openalex.org/W6677580257","https://openalex.org/W6774015895","https://openalex.org/W6784825895","https://openalex.org/W6796581206","https://openalex.org/W6802298259","https://openalex.org/W6847363464","https://openalex.org/W6853251322"],"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/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Recent":[0],"end-to-end":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"models":[6,128],"have":[7,88],"become":[8],"increasingly":[9],"larger,":[10],"making":[11],"them":[12],"particularly":[13],"challenging":[14],"to":[15,35,61,131],"be":[16],"deployed":[17],"on":[18,91,120],"resource-constrained":[19],"devices.":[20],"Model":[21],"quantisation":[22,60,80],"is":[23,50],"an":[24],"effective":[25],"solution":[26],"that":[27],"sometimes":[28],"causes":[29],"the":[30,63,92,95,132],"word":[31],"error":[32],"rate":[33],"(WER)":[34],"increase.":[36],"In":[37],"this":[38],"paper,":[39],"a":[40,46,72,101],"novel":[41],"strategy":[42],"of":[43,65],"personalisation":[44],"for":[45,78,85],"quantised":[47,121],"model":[48,59,79,105],"(PQM)":[49],"proposed,":[51],"which":[52],"combines":[53],"speaker":[54],"adaptive":[55],"training":[56],"(SAT)":[57],"with":[58,100],"improve":[62],"performance":[64],"heavily":[66],"compressed":[67],"models.":[68,136],"Specifically,":[69],"PQM":[70],"uses":[71],"4-bit":[73],"NormalFloat":[74],"Quantisation":[75],"(NF4)":[76],"approach":[77],"and":[81,94,107,113,123],"low-rank":[82],"adaptation":[83],"(LoRA)":[84],"SAT.":[86],"Experiments":[87],"been":[89],"performed":[90],"LibriSpeech":[93],"TED-LIUM":[96],"3":[97],"corpora.":[98],"Remarkably,":[99],"7x":[102],"reduction":[103],"in":[104],"size":[106],"1%":[108],"additional":[109],"speaker-specific":[110],"parameters,":[111],"15.1%":[112],"23.3%":[114],"relative":[115],"WER":[116],"reductions":[117],"were":[118],"achieved":[119],"Whisper":[122],"Conformer-based":[124],"attention-based":[125],"encoder-decoder":[126],"ASR":[127],"respectively,":[129],"comparing":[130],"original":[133],"full":[134],"precision":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}