{"id":"https://openalex.org/W4375869398","doi":"https://doi.org/10.1109/icassp49357.2023.10095268","title":"Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation","display_name":"Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869398","doi":"https://doi.org/10.1109/icassp49357.2023.10095268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102707172","display_name":"Liyong Guo","orcid":"https://orcid.org/0009-0002-2465-3914"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435428","display_name":"Xiaoyu Yang","orcid":"https://orcid.org/0000-0002-3570-8979"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013004114","display_name":"Quandong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quandong Wang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087994947","display_name":"Yuxiang Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Kong","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066643565","display_name":"Zengwei Yao","orcid":"https://orcid.org/0000-0002-2331-2387"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110945001","display_name":"Fan Cui","orcid":"https://orcid.org/0009-0007-0132-628X"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Cui","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040568268","display_name":"Fangjun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037914140","display_name":"Wei Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075614707","display_name":"Long Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010072640","display_name":"Mingshuang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshuang Luo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I4210150811","display_name":"MeaningCloud (Spain)","ror":"https://ror.org/05s565w61","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210150811"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Meaning.Team Inc,USA","Meaning.Team Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meaning.Team Inc,USA","institution_ids":["https://openalex.org/I4210150811"]},{"raw_affiliation_string":"Meaning.Team Inc, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]}],"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":6,"citation_normalized_percentile":null,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9948999881744385,"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/codebook","display_name":"Codebook","score":0.9647870063781738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6172902584075928},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5689800381660461},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5446020364761353},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5362076163291931},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.4353334307670593},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4200059175491333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41804665327072144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41755905747413635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36365967988967896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24931389093399048},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22575467824935913}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9647870063781738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172902584075928},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5689800381660461},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5446020364761353},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5362076163291931},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.4353334307670593},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4200059175491333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41804665327072144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41755905747413635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36365967988967896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24931389093399048},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22575467824935913},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1970491336","https://openalex.org/W2129935012","https://openalex.org/W2156333391","https://openalex.org/W2219249508","https://openalex.org/W2478708596","https://openalex.org/W2616180702","https://openalex.org/W2747874407","https://openalex.org/W2889871534","https://openalex.org/W2896457183","https://openalex.org/W2911629330","https://openalex.org/W2936774411","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3008008574","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3111562797","https://openalex.org/W3160628828","https://openalex.org/W3162649911","https://openalex.org/W3170863103","https://openalex.org/W3197642003","https://openalex.org/W3198715852","https://openalex.org/W3203453034","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4221161761","https://openalex.org/W4283700324","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6688816777","https://openalex.org/W6697274609","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6787040858","https://openalex.org/W6796761347","https://openalex.org/W6803378298","https://openalex.org/W6810673746"],"related_works":["https://openalex.org/W2017514583","https://openalex.org/W2352648934","https://openalex.org/W2391875658","https://openalex.org/W2100120615","https://openalex.org/W1929869830","https://openalex.org/W2017401491","https://openalex.org/W2387054321","https://openalex.org/W2158612577","https://openalex.org/W1681061148","https://openalex.org/W2084027797"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1],"(KD)":[2],"is":[3,20,59,111,160,195],"a":[4,17,28,83,88,106,114,125,199],"common":[5],"approach":[6,94],"to":[7,22,67,99],"improve":[8],"model":[9,19,65,116],"performance":[10,142],"in":[11,165],"automatic":[12],"speech":[13],"recognition":[14],"(ASR),":[15],"where":[16,113],"student":[18,115],"trained":[21],"imitate":[23],"the":[24,43,56,63,77,118,122,132,156,202],"output":[25],"behaviour":[26],"of":[27,79,124,192,201],"teacher":[29,37,50,64,80,97,128],"model.":[30,129],"However,":[31],"traditional":[32,144],"KD":[33,107,145],"methods":[34,146],"suffer":[35],"from":[36,121],"label":[38,51,81],"storage":[39],"issue,":[40,55],"especially":[41],"when":[42],"training":[44,57,108],"corpora":[45],"are":[46],"large.":[47],"Although":[48],"on-the-fly":[49],"generation":[52,78],"tackles":[53],"this":[54,73,193],"speed":[58],"significantly":[60],"slower":[61],"as":[62,82,143,198],"has":[66],"be":[68],"evaluated":[69],"every":[70],"batch.":[71],"In":[72],"paper,":[74],"we":[75],"reformulate":[76],"codec":[84],"problem.":[85],"We":[86],"propose":[87],"novel":[89],"Multi-codebook":[90],"Vector":[91],"Quantization":[92],"(MVQ)":[93],"that":[95,137],"compresses":[96],"embeddings":[98,123],"codebook":[100],"indexes":[101],"(CI).":[102],"Based":[103],"on":[104,131,179],"this,":[105],"framework":[109,139,163],"(MVQ-KD)":[110],"proposed":[112],"predicts":[117],"CI":[119],"generated":[120],"self-supervised":[126],"pre-trained":[127],"Experiments":[130],"LibriSpeech":[133,158],"clean-100":[134],"hour":[135],"show":[136],"MVQ-KD":[138,162],"achieves":[140],"comparable":[141],"(11,":[147],"12),":[148],"while":[149],"requiring":[150],"256":[151],"times":[152],"less":[153],"storage.":[154],"When":[155],"full":[157],"dataset":[159],"used,":[161],"results":[164],"13.8%":[166],"and":[167,181,183,185],"8.2%":[168],"relative":[169],"word":[170],"error":[171],"rate":[172],"reductions":[173],"(WERRs)":[174],"for":[175,187],"non":[176],"-streaming":[177],"transducer":[178],"test-clean":[180],"test-other":[182],"4.0%":[184],"4.9%":[186],"streaming":[188],"transducer.":[189],"The":[190],"implementation":[191],"work":[194],"already":[196],"released":[197],"part":[200],"open-source":[203],"project":[204],"icefall":[205],"<sup":[206],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[208],".":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}