{"id":"https://openalex.org/W4408352627","doi":"https://doi.org/10.1109/icassp49660.2025.10889332","title":"NTC-KWS: Noise-aware CTC for Robust Keyword Spotting","display_name":"NTC-KWS: Noise-aware CTC for Robust Keyword Spotting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352627","doi":"https://doi.org/10.1109/icassp49660.2025.10889332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889332","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":"conference-paper","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":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358563","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0001-9056-291X"},"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,China"],"raw_orcid":null,"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,China","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,China"],"raw_orcid":null,"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,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102913261","display_name":"Jiaqi Guo","orcid":"https://orcid.org/0009-0005-4168-5098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Guo","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342504","display_name":"Xu Li","orcid":"https://orcid.org/0009-0004-7507-4669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723777","display_name":"Wen Ding","orcid":"https://orcid.org/0009-0005-7628-4614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Ding","raw_affiliation_strings":["NVIDIA,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074843536","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0003-2436-5162"},"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,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9921000003814697,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9921000003814697,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9440000057220459,"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/keyword-spotting","display_name":"Keyword spotting","score":0.895382285118103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6892868280410767},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6144421100616455},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5210889577865601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46429142355918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28609445691108704}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.895382285118103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892868280410767},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6144421100616455},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5210889577865601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46429142355918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28609445691108704},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889332","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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2034940213","https://openalex.org/W2046932483","https://openalex.org/W2063721546","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2748659049","https://openalex.org/W2889017397","https://openalex.org/W2936774411","https://openalex.org/W2962707338","https://openalex.org/W2963308316","https://openalex.org/W2963628261","https://openalex.org/W2963977978","https://openalex.org/W2972541922","https://openalex.org/W3096421563","https://openalex.org/W3097878195","https://openalex.org/W3101731215","https://openalex.org/W3160405885","https://openalex.org/W3161425572","https://openalex.org/W3163237592","https://openalex.org/W3176579201","https://openalex.org/W4206567542","https://openalex.org/W4224916427","https://openalex.org/W4224932156","https://openalex.org/W4372267500","https://openalex.org/W4385822513","https://openalex.org/W4385822648","https://openalex.org/W4391021555","https://openalex.org/W4392904393","https://openalex.org/W4392904576","https://openalex.org/W4392932011","https://openalex.org/W4402111963","https://openalex.org/W4408354367","https://openalex.org/W6727249380","https://openalex.org/W6774097463"],"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":{"In":[0],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5],"a":[6,68],"growing":[7],"interest":[8],"in":[9,48,79,155],"designing":[10],"small-footprint":[11],"yet":[12],"effective":[13],"Connectionist":[14],"Temporal":[15],"Classification":[16],"based":[17,102],"keyword":[18],"spotting":[19],"(CTC-KWS)":[20],"systems.":[21],"They":[22],"are":[23],"typically":[24],"deployed":[25],"on":[26,32,103,130],"low-resource":[27],"computing":[28],"platforms,":[29],"where":[30],"limitations":[31],"model":[33,77],"size":[34],"and":[35,50,54,99,117,123,132,144],"computational":[36],"capacity":[37],"create":[38],"bottlenecks":[39],"under":[40,83],"complicated":[41],"acoustic":[42,149],"scenarios.":[43,158],"Such":[44],"constraints":[45],"often":[46],"result":[47],"overfitting":[49],"confusion":[51],"between":[52],"keywords":[53],"background":[55],"noise,":[56],"leading":[57],"to":[58,75,112,120],"high":[59],"false":[60],"alarms.":[61],"To":[62],"address":[63,113],"these":[64],"issues,":[65],"we":[66],"propose":[67],"noise-aware":[69],"CTC-based":[70],"KWS":[71],"(NTC-KWS)":[72],"framework":[73],"designed":[74],"enhance":[76],"robustness":[78],"noisy":[80,133],"environments,":[81],"particularly":[82,152],"extremely":[84],"low":[85,156],"signal-to-noise":[86],"ratios.":[87],"Our":[88],"approach":[89],"introduces":[90],"two":[91],"additional":[92],"noise-modeling":[93],"wildcard":[94],"arcs":[95,111,119],"into":[96],"the":[97],"training":[98],"decoding":[100],"processes":[101],"weighted":[104],"finite":[105],"state":[106],"transducer":[107],"(WFST)":[108],"graphs:":[109],"self-loop":[110],"noise":[114],"insertion":[115],"errors":[116],"bypass":[118],"handle":[121],"masking":[122],"interference":[124],"caused":[125],"by":[126],"excessive":[127],"noise.":[128],"Experiments":[129],"clean":[131],"Hey":[134],"Snips":[135],"show":[136],"that":[137],"NTC-KWS":[138],"outperforms":[139],"state-of-the-art":[140],"(SOTA)":[141],"end-to-end":[142],"systems":[143],"CTC-KWS":[145],"baselines":[146],"across":[147],"various":[148],"conditions,":[150],"with":[151],"strong":[153],"performance":[154],"SNR":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}