{"id":"https://openalex.org/W4392904393","doi":"https://doi.org/10.1109/icassp48485.2024.10446909","title":"TDT-KWS: Fast and Accurate Keyword Spotting Using Token-and-Duration Transducer","display_name":"TDT-KWS: Fast and Accurate Keyword Spotting Using Token-and-Duration Transducer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904393","doi":"https://doi.org/10.1109/icassp48485.2024.10446909"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5103250176","display_name":"Yu Xi","orcid":"https://orcid.org/0000-0003-0498-0328"},"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":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348668","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-9923-4346"},"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":"Hao Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086417695","display_name":"Baochen Yang","orcid":"https://orcid.org/0000-0002-0494-0361"},"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":"Baochen Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358581","display_name":"Haoyu Li","orcid":"https://orcid.org/0009-0004-9836-7747"},"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":"Haoyu Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409299","display_name":"Xu H","orcid":"https://orcid.org/0009-0001-1201-443X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["NVIDIA,U.S.A","NVIDIA, U.S.A"],"affiliations":[{"raw_affiliation_string":"NVIDIA,U.S.A","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, U.S.A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103250176"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.0672,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88010103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11351","last_page":"11355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9970999956130981,"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":0.8677583932876587},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8660956025123596},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7905751466751099},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.725469172000885},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6331759095191956},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5829107761383057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5054688453674316},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4442320466041565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4433954060077667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2020764946937561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677583932876587},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8660956025123596},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7905751466751099},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.725469172000885},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6331759095191956},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5829107761383057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5054688453674316},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4442320466041565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4433954060077667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2020764946937561},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2034940213","https://openalex.org/W2407080277","https://openalex.org/W2783089003","https://openalex.org/W2936774411","https://openalex.org/W2962707338","https://openalex.org/W2963308316","https://openalex.org/W2972541922","https://openalex.org/W2976556660","https://openalex.org/W3015639015","https://openalex.org/W3016010032","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3160405885","https://openalex.org/W3161425572","https://openalex.org/W3163582231","https://openalex.org/W4224137820","https://openalex.org/W4283828241","https://openalex.org/W4288088457","https://openalex.org/W6638749077","https://openalex.org/W6756383738","https://openalex.org/W6767671539","https://openalex.org/W6769806307","https://openalex.org/W6851766456"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Designing":[0],"an":[1],"efficient":[2],"keyword":[3,80],"spotting":[4],"(KWS)":[5],"system":[6],"that":[7,44,137],"delivers":[8],"exceptional":[9],"performance":[10,121],"on":[11,89],"resource-constrained":[12],"edge":[13],"devices":[14],"has":[15],"long":[16],"been":[17],"a":[18,29,66],"subject":[19],"of":[20],"significant":[21,131],"attention.":[22],"Existing":[23],"KWS":[24,61,68],"search":[25,33,81],"algorithms":[26],"typically":[27],"follow":[28],"frame-synchronous":[30],"approach,":[31],"where":[32],"decisions":[34],"are":[35,47],"made":[36],"repeatedly":[37],"at":[38],"each":[39],"frame":[40],"despite":[41],"the":[42,91],"fact":[43],"most":[45],"frames":[46],"keyword-irrelevant.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53,65],"TDT-KWS,":[54],"which":[55,75],"leverages":[56],"token-and-duration":[57],"Transducers":[58],"(TDT)":[59],"for":[60,72],"tasks.":[62],"We":[63],"also":[64],"novel":[67],"task-specific":[69],"decoding":[70,110],"algorithm":[71,102],"Transducer-based":[73],"models,":[74],"supports":[76],"highly":[77],"effective":[78],"frame-asynchronous":[79],"in":[82],"streaming":[83],"speech":[84],"scenarios.":[85],"With":[86],"evaluations":[87],"conducted":[88],"both":[90,123],"public":[92],"Hey":[93],"Snips":[94],"and":[95,125],"self-constructed":[96],"LibriKWS-20":[97],"datasets,":[98],"our":[99],"proposed":[100],"KWS-decoding":[101],"produces":[103],"more":[104,140],"accurate":[105],"results":[106],"than":[107,122],"conventional":[108],"ASR":[109],"algorithms.":[111],"Additionally,":[112],"TDTKWS":[113],"achieves":[114],"on-par":[115],"or":[116],"better":[117],"wake":[118],"word":[119],"detection":[120],"RNN-T":[124,147],"traditional":[126],"TDT-ASR":[127],"systems":[128],"while":[129],"achieving":[130],"inference":[132],"speed-up.":[133],"Furthermore,":[134],"experiments":[135],"show":[136],"TDT-KWS":[138],"is":[139],"robust":[141],"to":[142,146],"noisy":[143],"environments":[144],"compared":[145],"KWS.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
