{"id":"https://openalex.org/W4408355176","doi":"https://doi.org/10.1109/icassp49660.2025.10890369","title":"Adaptive Decoding for Efficient Automatic Speech Recognition","display_name":"Adaptive Decoding for Efficient Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355176","doi":"https://doi.org/10.1109/icassp49660.2025.10890369"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5078038985","display_name":"Xiangnan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangnan Ma","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030745240","display_name":"Peizhuo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peizhuo Liu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349349","display_name":"Yuhao Zhang","orcid":"https://orcid.org/0000-0002-8848-5924"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005320321","display_name":"Kaiqi Kou","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqi Kou","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112431965","display_name":"Chenghao Gao","orcid":"https://orcid.org/0000-0002-8942-3100"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghao Gao","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370155","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0000-0002-6537-7007"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078038985"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02080392,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9269999861717224,"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":0.9269999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.795627236366272},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7706141471862793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7487760782241821},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4425647556781769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3759644329547882},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13017380237579346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795627236366272},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7706141471862793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7487760782241821},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4425647556781769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3759644329547882},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13017380237579346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2487858831","https://openalex.org/W2519314406","https://openalex.org/W2892009249","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2964213727","https://openalex.org/W3085139254","https://openalex.org/W3097777922","https://openalex.org/W3184241125","https://openalex.org/W3196784225","https://openalex.org/W3197813307","https://openalex.org/W3209059054","https://openalex.org/W3211278025","https://openalex.org/W3211525823","https://openalex.org/W4221167707","https://openalex.org/W4385245566","https://openalex.org/W4385822841","https://openalex.org/W6681150705","https://openalex.org/W6744013678","https://openalex.org/W6784050962","https://openalex.org/W6802318714","https://openalex.org/W6838322825"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2541680182","https://openalex.org/W2166699153"],"abstract_inverted_index":{"The":[0],"latency":[1],"and":[2],"computation":[3],"demand":[4],"of":[5,30,64,111,117],"End-to-end":[6],"(E2E)":[7],"automatic":[8],"speech":[9,69,112],"recognition":[10],"(ASR)":[11],"models":[12],"hinder":[13],"their":[14],"deployment":[15],"on":[16,60],"lightweight":[17],"devices.":[18],"Despite":[19],"there":[20],"are":[21],"many":[22],"methods":[23],"proposed":[24],"for":[25,43],"efficiency,":[26],"the":[27,31,57,61,73,80,99,115],"computational":[28],"burden":[29],"output":[32],"layer":[33],"with":[34,86],"a":[35,40,87,108],"large":[36],"vocabulary":[37,75],"is":[38],"still":[39],"major":[41],"challenge":[42],"decoders.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,71],"propose":[49],"an":[50],"adaptive":[51],"decoding":[52],"method":[53,96],"(ADD)":[54],"to":[55,82],"reduce":[56],"latency.":[58],"Based":[59],"vocal":[62],"features":[63],"words":[65],"like":[66],"phonemes":[67],"or":[68],"units,":[70],"cluster":[72],"original":[74],"into":[76],"small":[77],"sets,":[78],"allowing":[79],"model":[81],"inference":[83],"more":[84],"efficiently":[85],"smaller":[88],"search":[89],"space.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"that":[94],"our":[95],"significantly":[97],"reduces":[98],"calculation":[100],"FLOPs":[101],"while":[102],"maintaining":[103],"performance.":[104],"We":[105],"also":[106],"provide":[107],"deeper":[109],"understanding":[110],"units":[113],"from":[114],"perspective":[116],"phonemes.":[118]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}