{"id":"https://openalex.org/W4406461696","doi":"https://doi.org/10.1109/slt61566.2024.10832149","title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","display_name":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461696","doi":"https://doi.org/10.1109/slt61566.2024.10832149"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5080901723","display_name":"Hang Shao","orcid":"https://orcid.org/0000-0002-1322-4789"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Shao","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050191160","display_name":"Bei Liu","orcid":"https://orcid.org/0000-0002-0330-9957"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391659","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-5367-7056"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080901723"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82769361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"246"},"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":0.9990000128746033,"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":0.9980999827384949,"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":0.7193450927734375},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6564251184463501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6518309116363525},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6273608207702637},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6155589818954468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4568409025669098},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3446226418018341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33181333541870117},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09121793508529663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08154597878456116},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0624520480632782},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.045457303524017334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193450927734375},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6564251184463501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6518309116363525},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6273608207702637},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6155589818954468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4568409025669098},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3446226418018341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33181333541870117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09121793508529663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08154597878456116},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0624520480632782},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.045457303524017334},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1690739335","https://openalex.org/W2896409484","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2973049979","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3105966348","https://openalex.org/W3187822143","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224821750","https://openalex.org/W4226126941","https://openalex.org/W4297841557","https://openalex.org/W4297841866","https://openalex.org/W4311000453","https://openalex.org/W4375869065","https://openalex.org/W4385245566","https://openalex.org/W4385823182","https://openalex.org/W4385823417","https://openalex.org/W4388275972","https://openalex.org/W4392903564","https://openalex.org/W4392904185","https://openalex.org/W6631190155","https://openalex.org/W6637551013","https://openalex.org/W6755843862","https://openalex.org/W6768086466","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6798952882","https://openalex.org/W6847363464","https://openalex.org/W6857879404"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2344382886","https://openalex.org/W4396737233","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491"],"abstract_inverted_index":{"As":[0],"a":[1,28,44,51,112],"popular":[2],"multilingual":[3,19,66,78],"and":[4,32],"multitask":[5],"pre-trained":[6],"speech":[7],"model,":[8],"Whisper":[9,23,37,82],"has":[10],"the":[11,77],"problem":[12],"of":[13,15,80],"curse":[14],"multilinguality.":[16],"To":[17],"enhance":[18,76],"capabilities":[20,79],"in":[21,92,111],"small":[22,81],"models,":[24],"we":[25,42],"propose":[26,43],"DQ-Whisper,":[27],"novel":[29,45],"joint":[30],"distillation":[31,48,53,72],"quantization":[33,59,103],"framework":[34,54],"to":[35,57,89],"compress":[36],"for":[38],"efficient":[39],"inference.":[40],"Firstly,":[41],"dynamic":[46],"matching":[47],"strategy.":[49],"Then,":[50],"quantization-aware":[52],"is":[55,95,104],"introduced":[56],"integrate":[58],"with":[60,97,106],"distillation.":[61],"Experimental":[62],"results":[63],"on":[64],"various":[65],"datasets":[67],"show":[68],"that":[69],"our":[70],"suggested":[71],"approach":[73],"can":[74,109],"effectively":[75],"models":[83],"without":[84],"increasing":[85],"computational":[86],"costs.":[87],"Up":[88],"5.18x":[90],"reduction":[91],"model":[93],"size":[94],"achieved":[96],"marginal":[98],"performance":[99],"degradation.":[100],"In":[101],"addition,":[102],"compatible":[105],"distillation,":[107],"which":[108],"result":[110],"higher":[113],"compression":[114],"rate.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}