{"id":"https://openalex.org/W7148537690","doi":"https://doi.org/10.1109/asru65441.2025.11434761","title":"Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization","display_name":"Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148537690","doi":"https://doi.org/10.1109/asru65441.2025.11434761"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5121233921","display_name":"Jian You","orcid":null},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian You","raw_affiliation_strings":["Cisco Systems,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Cisco Systems,Shanghai,China","institution_ids":["https://openalex.org/I151281966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375325","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0003-0682-9525"},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Li","raw_affiliation_strings":["Cisco Systems,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Cisco Systems,Shanghai,China","institution_ids":["https://openalex.org/I151281966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010842305","display_name":"Erwan Zerhouni","orcid":null},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erwan Zerhouni","raw_affiliation_strings":["Cisco Systems,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Cisco Systems,Shanghai,China","institution_ids":["https://openalex.org/I151281966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121233921"],"corresponding_institution_ids":["https://openalex.org/I151281966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87575625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7892000079154968,"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":0.7892000079154968,"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":0.11209999769926071,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5468000173568726},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.325300008058548},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.29829999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.585099995136261},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2694000005722046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2911629330","https://openalex.org/W2937326859","https://openalex.org/W2962826786","https://openalex.org/W2963979492","https://openalex.org/W3094965760","https://openalex.org/W3095192922","https://openalex.org/W3096718507","https://openalex.org/W3097777922","https://openalex.org/W3160648428","https://openalex.org/W3162649911","https://openalex.org/W3183246637","https://openalex.org/W3196771368","https://openalex.org/W3198587774","https://openalex.org/W3198715852","https://openalex.org/W3203453034","https://openalex.org/W3209059054","https://openalex.org/W4225297945","https://openalex.org/W4226272674","https://openalex.org/W4284974527","https://openalex.org/W4297727296","https://openalex.org/W4297841364","https://openalex.org/W4297841655","https://openalex.org/W4375869398","https://openalex.org/W4385245566","https://openalex.org/W4391021797","https://openalex.org/W4392902925","https://openalex.org/W4392910583","https://openalex.org/W4402112374"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"models":[5,18,51],"typically":[6],"produce":[7],"outputs":[8],"as":[9],"normalized":[10],"texts":[11],"lacking":[12],"punctuation":[13,56,105,110],"and":[14,28,57,103,106,108,119],"capitalization,":[15,58,107],"necessitating":[16],"post-processing":[17],"to":[19,31,38,46],"enhance":[20],"readability.":[21],"This":[22],"approach,":[23],"however,":[24],"introduces":[25],"additional":[26],"complexity":[27],"latency":[29],"due":[30],"the":[32,116],"cascaded":[33],"system":[34],"design.":[35],"In":[36,64],"response":[37],"this":[39,60,65],"challenge,":[40],"there":[41],"is":[42],"a":[43],"growing":[44],"trend":[45],"develop":[47],"end-to-end":[48],"(E2E)":[49],"ASR":[50,74],"capable":[52],"of":[53],"directly":[54],"predicting":[55],"though":[59],"area":[61],"remains":[62],"underexplored.":[63],"paper,":[66],"we":[67],"propose":[68],"an":[69],"enhanced":[70],"fully":[71],"formatted":[72],"E2E":[73],"model":[75,91,125],"that":[76,89,123],"leverages":[77],"knowledge":[78],"distillation":[79],"(KD)":[80],"through":[81],"multi-codebook":[82],"vector":[83],"quantization":[84],"(MVQ).":[85],"Experimental":[86],"results":[87],"demonstrate":[88],"our":[90,124],"significantly":[92],"outperforms":[93],"previous":[94],"works":[95],"in":[96,109],"word":[97],"error":[98,111],"rate":[99,112],"(WER)":[100],"both":[101],"with":[102],"without":[104],"(PER).":[113],"Evaluations":[114],"on":[115],"LibriSpeech-PC":[117],"test-clean":[118],"test-other":[120],"subsets":[121],"show":[122],"achieves":[126],"state-of-the-art":[127],"results.":[128]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}