{"id":"https://openalex.org/W4398795596","doi":"https://doi.org/10.1109/icasspw62465.2024.10627382","title":"Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation","display_name":"Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4398795596","doi":"https://doi.org/10.1109/icasspw62465.2024.10627382"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627382","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.13514","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100568412","display_name":"Muhammad Shakeel","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muhammad Shakeel","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,Saitama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,Saitama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05351175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"570","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9726999998092651,"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":0.9726999998092651,"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":0.9496999979019165,"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/joint","display_name":"Joint (building)","score":0.8340798616409302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7616328597068787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5892884731292725},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.553674042224884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32863694429397583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3256286084651947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09822645783424377}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.8340798616409302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616328597068787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5892884731292725},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.553674042224884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32863694429397583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3256286084651947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09822645783424377},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627382","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.13514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13514","pdf_url":"https://arxiv.org/pdf/2405.13514","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.13514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.13514","pdf_url":"https://arxiv.org/pdf/2405.13514","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398795596.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963414781","https://openalex.org/W2982242214","https://openalex.org/W3007433671","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3035321581","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3160766462","https://openalex.org/W3162649911","https://openalex.org/W3163203022","https://openalex.org/W3163793923","https://openalex.org/W3163907627","https://openalex.org/W4223988178","https://openalex.org/W4296068782","https://openalex.org/W4297841343","https://openalex.org/W4385823173","https://openalex.org/W4385823261","https://openalex.org/W4388017359","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6790121257","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2768175398","https://openalex.org/W2888483922","https://openalex.org/W2344382886","https://openalex.org/W4396737233","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W3204019825"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3,24,40],"recognition":[4],"(ASR)":[5],"can":[6],"operate":[7,47],"in":[8,26,48],"two":[9,106],"modes:":[10],"streaming":[11,63,124],"and":[12,18,64,70,95,109,126],"non-streaming,":[13],"each":[14],"with":[15],"its":[16],"pros":[17],"cons.":[19],"Streaming":[20],"ASR":[21,35,66,82,132],"processes":[22],"the":[23,38,77,91,105],"frames":[25],"real-time":[27],"as":[28],"it":[29],"is":[30],"being":[31],"received,":[32],"while":[33],"non-streaming":[34,65,131],"waits":[36],"for":[37,123,130],"entire":[39],"utterance;":[41],"thus,":[42],"professionals":[43],"may":[44],"have":[45],"to":[46,51,89,138],"either":[49],"mode":[50,93],"satisfy":[52],"their":[53],"application.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,74],"present":[59],"joint":[60],"optimization":[61],"of":[62,80],"based":[67],"on":[68,121],"multi-decoder":[69],"knowledge":[71,102],"distillation.":[72],"Primarily,":[73],"study":[75],"1)":[76],"encoder":[78],"integration":[79],"these":[81],"modules,":[83],"followed":[84],"by":[85,98],"2)":[86],"separate":[87],"decoders":[88],"make":[90],"switching":[92],"flexible,":[94],"enhancing":[96],"performance":[97],"3)":[99],"incorporating":[100],"similarity-preserving":[101],"distillation":[103],"between":[104],"modular":[107],"encoders":[108],"decoders.":[110],"Evaluation":[111],"results":[112],"show":[113],"2.6%-5.3%":[114],"relative":[115,128],"character":[116],"error":[117],"rate":[118],"reductions":[119],"(CERR)":[120],"CSJ":[122],"ASR,":[125],"8.3%-9.7%":[127],"CERRs":[129],"within":[133],"a":[134],"single":[135],"model":[136],"compared":[137],"multiple":[139],"standalone":[140],"modules.":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-05-25T00:00:00"}