{"id":"https://openalex.org/W4406461919","doi":"https://doi.org/10.1109/slt61566.2024.10832336","title":"Effective Noise-Aware Data Simulation For Domain-Adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation","display_name":"Effective Noise-Aware Data Simulation For Domain-Adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461919","doi":"https://doi.org/10.1109/slt61566.2024.10832336"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5006997733","display_name":"Chien-Chun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Chun Wang","raw_affiliation_strings":["National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["United-Link Co., Ltd,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United-Link Co., Ltd,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["United-Link Co., Ltd,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United-Link Co., Ltd,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052214631","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Dept. Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Computer Science, Academia Sinica,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7489266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.759577751159668},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6927568912506104},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4863300919532776},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4519963562488556},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.43727338314056396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4252273440361023},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2774043679237366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24696069955825806},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0686982274055481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759577751159668},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6927568912506104},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4863300919532776},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4519963562488556},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.43727338314056396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4252273440361023},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2774043679237366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24696069955825806},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0686982274055481},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1983108229","https://openalex.org/W2141998673","https://openalex.org/W2593116425","https://openalex.org/W2593768305","https://openalex.org/W2603567530","https://openalex.org/W2760103357","https://openalex.org/W2891138528","https://openalex.org/W2897371647","https://openalex.org/W2962843322","https://openalex.org/W2963453742","https://openalex.org/W2963522845","https://openalex.org/W2973220283","https://openalex.org/W3031135612","https://openalex.org/W3097945073","https://openalex.org/W3163418064","https://openalex.org/W3196667132","https://openalex.org/W4221143458","https://openalex.org/W4221156109","https://openalex.org/W4296069339","https://openalex.org/W4312048190","https://openalex.org/W4375868977","https://openalex.org/W4385822340","https://openalex.org/W4402111962","https://openalex.org/W6631190155","https://openalex.org/W6695692224","https://openalex.org/W6748312029","https://openalex.org/W6762114000","https://openalex.org/W6846517224","https://openalex.org/W6848208918"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W2373767407","https://openalex.org/W2516933085","https://openalex.org/W3168109306","https://openalex.org/W2089240210","https://openalex.org/W2358461432","https://openalex.org/W3176700874","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Cross-domain":[0],"speech":[1,59],"enhancement":[2],"(SE)":[3],"is":[4],"often":[5],"faced":[6],"with":[7,54],"severe":[8],"challenges":[9],"due":[10],"to":[11,25,42,68,81,86,125,128],"the":[12,79,87,93,97,104,116,123,134],"scarcity":[13],"of":[14,96,106],"noise":[15,66,70,117,130],"and":[16,30,49],"background":[17],"information":[18],"in":[19],"an":[20,145],"unseen":[21,129],"target":[22,57,88],"domain,":[23],"leading":[24],"a":[26,37,65],"mismatch":[27],"between":[28],"training":[29],"test":[31],"conditions.":[32,131],"This":[33],"study":[34],"puts":[35],"forward":[36],"novel":[38],"data":[39,151],"simulation":[40],"method":[41,63,143],"address":[43],"this":[44],"issue,":[45],"leveraging":[46],"noise-extractive":[47],"techniques":[48],"generative":[50],"adversarial":[51],"networks":[52],"(GANs)":[53],"only":[55],"limited":[56],"noisy":[58],"data.":[60,74],"Notably,":[61],"our":[62,140],"employs":[64],"encoder":[67],"extract":[69],"embeddings":[71,76,118],"from":[72],"target-domain":[73],"These":[75],"aptly":[77],"guide":[78],"generator":[80],"synthesize":[82],"utterances":[83],"acoustically":[84],"fitted":[85],"domain":[89],"while":[90],"authentically":[91],"preserving":[92],"phonetic":[94],"content":[95],"input":[98],"clean":[99],"speech.":[100],"Furthermore,":[101],"we":[102],"introduce":[103],"notion":[105],"dynamic":[107],"stochastic":[108],"perturbation,":[109],"which":[110],"can":[111],"inject":[112],"controlled":[113],"perturbations":[114],"into":[115],"during":[119],"inference,":[120],"thereby":[121],"enabling":[122],"model":[124],"generalize":[126],"well":[127],"Experiments":[132],"on":[133,150],"VoiceBank-DEMAND":[135],"benchmark":[136],"dataset":[137],"demonstrate":[138],"that":[139],"domain-adaptive":[141],"SE":[142],"outperforms":[144],"existing":[146],"strong":[147],"baseline":[148],"based":[149],"simulation.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}