{"id":"https://openalex.org/W4387968129","doi":"https://doi.org/10.1145/3581783.3612173","title":"TE-KWS: Text-Informed Speech Enhancement for Noise-Robust Keyword Spotting","display_name":"TE-KWS: Text-Informed Speech Enhancement for Noise-Robust Keyword Spotting","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968129","doi":"https://doi.org/10.1145/3581783.3612173"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612173","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612173","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407412","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0002-2286-5756"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]},{"id":"https://openalex.org/I4210150411","display_name":"Shandong Youth University of Political Science","ror":"https://ror.org/04bwp4t29","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210150411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Jiangsu University & Shandong Youth University of Political Science, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-2286-5756","affiliations":[{"raw_affiliation_string":"Jiangsu University & Shandong Youth University of Political Science, Zhenjiang, China","institution_ids":["https://openalex.org/I4210150411","https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0616-4431","affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008699574","display_name":"Lijian Gao","orcid":"https://orcid.org/0000-0002-6458-0660"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijian Gao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-6458-0660","affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060265416","display_name":"Qinghua Ren","orcid":"https://orcid.org/0000-0002-3441-4514"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Ren","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-3441-4514","affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023122827","display_name":"Zhenghan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghan Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1841-539X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101897241","display_name":"Ming Dong","orcid":"https://orcid.org/0000-0001-8133-7809"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Dong","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"raw_orcid":"https://orcid.org/0000-0001-8133-7809","affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1848,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44991952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9987000226974487,"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":0.8506510853767395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787340521812439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7574390172958374},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6514646410942078},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.642952561378479},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6374593377113342},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5240338444709778},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.4439358711242676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4353474974632263},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4314190149307251}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8506510853767395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787340521812439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7574390172958374},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6514646410942078},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.642952561378479},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6374593377113342},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5240338444709778},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.4439358711242676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4353474974632263},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4314190149307251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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:10.1145/3581783.3612173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612173","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612173","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7158469337","display_name":null,"funder_award_id":"62176106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8142338255","display_name":null,"funder_award_id":"U1836220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968129.pdf","grobid_xml":"https://content.openalex.org/works/W4387968129.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2086139506","https://openalex.org/W2096943734","https://openalex.org/W2144404214","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2407023693","https://openalex.org/W2408688265","https://openalex.org/W2506203739","https://openalex.org/W2514828952","https://openalex.org/W2558649592","https://openalex.org/W2589857635","https://openalex.org/W2603567530","https://openalex.org/W2618530766","https://openalex.org/W2635471793","https://openalex.org/W2734774145","https://openalex.org/W2748659049","https://openalex.org/W2766910928","https://openalex.org/W2767071179","https://openalex.org/W2783652918","https://openalex.org/W2889827072","https://openalex.org/W2930364467","https://openalex.org/W2938386503","https://openalex.org/W2952218014","https://openalex.org/W2955926808","https://openalex.org/W2962866211","https://openalex.org/W2963390466","https://openalex.org/W2963414149","https://openalex.org/W2963446712","https://openalex.org/W2963628261","https://openalex.org/W2963881567","https://openalex.org/W2972951785","https://openalex.org/W2972992323","https://openalex.org/W2973226577","https://openalex.org/W2991405316","https://openalex.org/W2997739323","https://openalex.org/W2997987128","https://openalex.org/W2998161426","https://openalex.org/W2998459790","https://openalex.org/W3016218307","https://openalex.org/W3017216675","https://openalex.org/W3025581723","https://openalex.org/W3048055188","https://openalex.org/W3095467524","https://openalex.org/W3097018422","https://openalex.org/W3127196078","https://openalex.org/W3158779859","https://openalex.org/W3197729725","https://openalex.org/W3206809722","https://openalex.org/W4224934178","https://openalex.org/W4255525331","https://openalex.org/W6777189519"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KWS)":[2],"presents":[3],"a":[4,57,170],"formidable":[5],"challenge,":[6],"particularly":[7],"in":[8,45],"high-noise":[9],"environments.":[10],"Traditional":[11],"denoising":[12,38,124,172],"algorithms":[13],"that":[14,23,218],"rely":[15],"solely":[16],"on":[17,176],"speech":[18,22,63,68,75,92,117,150,184],"have":[19],"difficulty":[20],"recovering":[21],"has":[24],"been":[25],"severely":[26],"corrupted":[27,226,233],"by":[28,147],"noise.":[29],"In":[30],"this":[31],"investigation,":[32],"we":[33],"develop":[34],"an":[35],"adaptive":[36],"text-informed":[37],"model":[39,110,125,144,189],"to":[40,111,201,209],"bolster":[41],"reliable":[42],"keyword":[43],"identification":[44],"the":[46,62,73,77,90,100,109,114,122,131,134,143,157,160,177,183,188,193,203,238],"presence":[47],"of":[48,89,133,187,205,242],"considerable":[49],"noise":[50],"degradation.":[51],"The":[52],"whole":[53,135],"proposed":[54,123],"TE-KWS":[55],"incorporates":[56],"tripartite":[58],"branch":[59,64,79,102,138,162],"structure,":[60],"where":[61],"(SB)":[65],"takes":[66],"noisy":[67],"as":[69],"input":[70,84,158],"which":[71,85,107],"provides":[72],"raw":[74],"information,":[76],"alignment":[78,96,115,137,154],"(AB)":[80,139],"accommodates":[81],"aligned":[82],"text":[83,94,101,106,161],"facilitates":[86],"accurate":[87],"restoration":[88,151,185],"corresponding":[91],"when":[93],"with":[95,166,207],"is":[97,140,145,164,174,199],"preserved,":[98],"and":[99,118,142,152,169,240],"(TB)":[103,163],"handles":[104],"unaligned":[105],"prompts":[108],"autonomously":[112],"learn":[113],"between":[116],"text.":[119],"To":[120],"make":[121],"more":[126],"beneficial":[127],"for":[128,159,190,231],"KWS,":[129],"following":[130],"training":[132],"model,the":[136],"frozen,":[141],"fine-tuned":[146],"leveraging":[148],"its":[149],"forced":[153],"capabilities.":[155],"Subsequently,":[156],"supplanted":[165],"designated":[167],"keywords,":[168],"heavier":[171],"penalty":[173],"applied":[175],"keywords":[178],"period,":[179],"thereby":[180],"explicitly":[181],"intensifying":[182],"ability":[186],"keywords.":[191],"Finally,":[192],"Combined":[194],"Adversarial":[195],"Domain":[196],"Adaptation":[197],"(CADA)":[198],"implemented":[200],"enhance":[202],"robustness":[204],"KWS":[206,245],"regard":[208],"data":[210],"pre-and":[211],"post-speech":[212],"enhancement":[213],"(SE).":[214],"Experimental":[215],"results":[216],"indicate":[217],"our":[219],"approach":[220],"not":[221],"only":[222],"markedly":[223],"ameliorates":[224],"highly":[225],"speech,":[227,234],"achieving":[228],"SOTA":[229],"performance":[230],"marginally":[232],"but":[235],"also":[236],"bolsters":[237],"efficacy":[239],"generalizability":[241],"prevailing":[243],"mainstream":[244],"models.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}