{"id":"https://openalex.org/W4392932011","doi":"https://doi.org/10.1109/icassp48485.2024.10447881","title":"Contrastive Learning with Audio Discrimination for Customizable Keyword Spotting in Continuous Speech","display_name":"Contrastive Learning with Audio Discrimination for Customizable Keyword Spotting in Continuous Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392932011","doi":"https://doi.org/10.1109/icassp48485.2024.10447881"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447881","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/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/A5100607010","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-6786-6501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"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","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","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":5,"corresponding_author_ids":["https://openalex.org/A5103250176"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.0007,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94179977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11666","last_page":"11670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/keyword-spotting","display_name":"Keyword spotting","score":0.852779746055603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8227934241294861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7744636535644531},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6610415577888489},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.523094654083252},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5116841793060303},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43297839164733887},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4158353805541992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40596795082092285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3550652861595154},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.32710739970207214},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.320750892162323},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.31714844703674316}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.852779746055603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227934241294861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7744636535644531},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6610415577888489},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.523094654083252},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5116841793060303},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43297839164733887},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4158353805541992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40596795082092285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3550652861595154},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.32710739970207214},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.320750892162323},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.31714844703674316},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447881","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"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":36,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1496120315","https://openalex.org/W1983205135","https://openalex.org/W2034940213","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2510945575","https://openalex.org/W2523246573","https://openalex.org/W2587529061","https://openalex.org/W2748659049","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2842511635","https://openalex.org/W2891722048","https://openalex.org/W2938873567","https://openalex.org/W2962980711","https://openalex.org/W2963308316","https://openalex.org/W2963414149","https://openalex.org/W2972613398","https://openalex.org/W3098773154","https://openalex.org/W3155772857","https://openalex.org/W3160257947","https://openalex.org/W3162273446","https://openalex.org/W3196509839","https://openalex.org/W4224932156","https://openalex.org/W4283767777","https://openalex.org/W4289243832","https://openalex.org/W4296069322","https://openalex.org/W4297808394","https://openalex.org/W4372260220","https://openalex.org/W4372346399","https://openalex.org/W4385822437","https://openalex.org/W4385823483","https://openalex.org/W6727249380","https://openalex.org/W6757022092","https://openalex.org/W6774314701"],"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":{"Customizable":[0],"keyword":[1,27,87],"spotting":[2],"(KWS)":[3],"in":[4,48],"continuous":[5,49,144],"speech":[6,145],"has":[7,21],"attracted":[8],"increasing":[9],"attention":[10],"due":[11],"to":[12,25,85,136,166],"its":[13],"real-world":[14],"application":[15],"potential.":[16],"While":[17],"contrastive":[18],"learning":[19,86],"(CL)":[20],"been":[22],"widely":[23],"used":[24],"extract":[26],"representations,":[28],"previous":[29,137],"CL":[30,79,106,138,160],"approaches":[31],"all":[32],"operate":[33],"on":[34,118,142],"pre-segmented":[35],"isolated":[36],"words":[37],"and":[38,52,93,104],"employ":[39],"only":[40,177],"audio-text":[41,91,105],"representations":[42],"matching":[43,92],"strategy.":[44],"However,":[45],"for":[46,62,111],"KWS":[47,168,172],"speech,":[50],"co-articulation":[51],"streaming":[53],"word":[54],"segmentation":[55],"can":[56],"easily":[57],"yield":[58],"similar":[59],"audio":[60,152,162],"patterns":[61],"different":[63],"texts,":[64],"which":[65],"may":[66],"consequently":[67],"trigger":[68],"false":[69],"alarms.":[70],"To":[71],"address":[72],"this":[73],"issue,":[74],"we":[75],"propose":[76],"a":[77],"novel":[78],"with":[80,89,173],"Audio":[81],"Discrimination":[82],"(CLAD)":[83],"approach":[84],"representation":[88],"both":[90,102],"audio-audio":[94,103],"discrimination":[95],"ability.":[96],"Here,":[97],"an":[98],"InfoNCE":[99,130],"loss":[100,131],"considering":[101],"data":[107],"pairs":[108],"is":[109],"employed":[110],"each":[112],"sliding":[113],"window":[114],"during":[115],"training.":[116],"Evaluations":[117],"the":[119,125,143,170],"open-source":[120],"LibriPhrase":[121],"dataset":[122,146],"show":[123],"that":[124],"use":[126],"of":[127],"sliding-window":[128],"level":[129],"yields":[132],"comparable":[133],"performance":[134,157],"compared":[135,165],"approaches.":[139],"Furthermore,":[140],"experiments":[141],"LibriSpeech":[147],"demonstrate":[148],"that,":[149],"by":[150],"incorporating":[151],"discrimination,":[153],"CLAD":[154,174],"achieves":[155,175],"significant":[156,182],"gain":[158],"over":[159],"without":[161],"discrimination.":[163],"Meanwhile,":[164],"two-stage":[167],"approaches,":[169],"end-to-end":[171],"not":[176],"better":[178],"performance,":[179],"but":[180],"also":[181],"speed-up.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}