{"id":"https://openalex.org/W4392904743","doi":"https://doi.org/10.1109/icassp48485.2024.10448083","title":"CSNet: Contrastive Siamese Network for Robust SLU","display_name":"CSNet: Contrastive Siamese Network for Robust SLU","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904743","doi":"https://doi.org/10.1109/icassp48485.2024.10448083"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448083","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448083","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/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei 2012 Labs.,Beijing,China","Huawei 2012 Labs., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei 2012 Labs.,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei 2012 Labs., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403018","display_name":"Min Zhang","orcid":"https://orcid.org/0009-0000-4185-940X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei 2012 Labs.,Beijing,China","Huawei 2012 Labs., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei 2012 Labs.,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei 2012 Labs., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012613066","display_name":"Daimeng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":["Huawei 2012 Labs.,Beijing,China","Huawei 2012 Labs., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei 2012 Labs.,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei 2012 Labs., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060023404","display_name":"Jiaxin Guo","orcid":"https://orcid.org/0000-0002-2314-8804"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Guo","raw_affiliation_strings":["Huawei 2012 Labs.,Beijing,China","Huawei 2012 Labs., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei 2012 Labs.,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei 2012 Labs., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038736812"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02632354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12797","last_page":"12801"},"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/T10181","display_name":"Natural Language Processing Techniques","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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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":0.8120643496513367},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6984953880310059},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6425395607948303},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6198223829269409},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.615104079246521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811111330986023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.553669810295105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5314995646476746},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47192955017089844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120643496513367},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6984953880310059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6425395607948303},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6198223829269409},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.615104079246521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811111330986023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.553669810295105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5314995646476746},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47192955017089844},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448083","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448083","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1975244201","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W3006901707","https://openalex.org/W3016256870","https://openalex.org/W3095552229","https://openalex.org/W3100460087","https://openalex.org/W3156636935","https://openalex.org/W3197744084","https://openalex.org/W4214768891","https://openalex.org/W4225403296","https://openalex.org/W4283218202","https://openalex.org/W4285819432","https://openalex.org/W4308793450","https://openalex.org/W4361200098","https://openalex.org/W4385571399","https://openalex.org/W4385571567","https://openalex.org/W4385572615","https://openalex.org/W4385807419","https://openalex.org/W4385822317","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"results":[4],"based":[5,15,108],"on":[6,16,52,109,120,141],"clean":[7,28,62,84,101,115],"references":[8],"are":[9,56],"much":[10],"more":[11],"accurate":[12],"than":[13],"those":[14],"ASR":[17,59,81,111],"transcripts":[18,29,60,63,82],"in":[19],"spoken":[20],"language":[21],"understanding":[22],"(SLU).":[23],"Effective":[24],"utilization":[25],"of":[26,58,80,127],"manually-checked":[27],"is":[30,64],"key":[31],"to":[32,45],"improving":[33],"SLU":[34,47,68],"performance.":[35],"This":[36],"paper":[37],"proposes":[38],"a":[39,105],"siamese":[40,50,95],"network":[41,51,96],"with":[42],"contrastive":[43,72],"learning":[44,73],"enhance":[46],"effects.":[48],"A":[49],"sentence":[53,106],"pairs":[54],"that":[55],"composed":[57],"and":[61,83,113],"used":[65],"for":[66,117],"the":[67,76,94,99,110,125,133,142],"task.":[69],"During":[70,86],"training,":[71],"brings":[74],"closer":[75],"sentence-level":[77],"semantic":[78,91],"representations":[79],"transcripts.":[85],"inference,":[87],"k-nearest":[88],"neighbors":[89],"(KNN)":[90],"search":[92],"via":[93],"first":[97],"finds":[98],"pseudo":[100,114],"transcript,":[102],"then":[103],"forms":[104],"pair":[107],"transcript":[112,116],"prediction.":[118],"Experiments":[119],"three":[121],"benchmark":[122],"datasets":[123],"prove":[124],"effectiveness":[126],"our":[128],"proposed":[129],"approach,":[130],"which":[131],"improves":[132],"Intent":[134],"Classification":[135],"(IC)":[136],"performance":[137],"by":[138],"over":[139],"1.3%":[140],"SLURP":[143],"dataset.":[144]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}