{"id":"https://openalex.org/W4408356262","doi":"https://doi.org/10.1109/icassp49660.2025.10887613","title":"Text-guided Device-realistic Sound Generation for Fiber-based Sound Event Classification","display_name":"Text-guided Device-realistic Sound Generation for Fiber-based Sound Event Classification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356262","doi":"https://doi.org/10.1109/icassp49660.2025.10887613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887613","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":"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/A5024938442","display_name":"Wataru Kohno","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wataru Kohno","raw_affiliation_strings":["NEC Laboratories America, Inc,The United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc,The United States of America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059521640","display_name":"Noriyuki Tonami","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noriyuki Tonami","raw_affiliation_strings":["NEC Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation,Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064705538","display_name":"Jian Fang","orcid":"https://orcid.org/0000-0002-9870-2136"},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Fang","raw_affiliation_strings":["NEC Laboratories America, Inc,The United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc,The United States of America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101411710","display_name":"Shaobo Han","orcid":"https://orcid.org/0000-0003-2545-7114"},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaobo Han","raw_affiliation_strings":["NEC Laboratories America, Inc,The United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc,The United States of America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110936166","display_name":"Jingchen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingchen Sun","raw_affiliation_strings":["The State University of New York at Buffalo,NEC Laboratories America, Inc,The United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The State University of New York at Buffalo,NEC Laboratories America, Inc,The United States of America","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427883","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0001-5822-5382"},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["NEC Laboratories America, Inc,The United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc,The United States of America","institution_ids":["https://openalex.org/I4210107353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7073,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88896093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9484000205993652,"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/sound","display_name":"Sound (geography)","score":0.7090741991996765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899967193603516},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5572797060012817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4680827260017395},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4590929448604584},{"id":"https://openalex.org/keywords/fiber","display_name":"Fiber","score":0.44790196418762207},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13177141547203064},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1292826235294342}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7090741991996765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899967193603516},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5572797060012817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4680827260017395},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4590929448604584},{"id":"https://openalex.org/C519885992","wikidata":"https://www.wikidata.org/wiki/Q161","display_name":"Fiber","level":2,"score":0.44790196418762207},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13177141547203064},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1292826235294342},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887613","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2509065397","https://openalex.org/W2947066362","https://openalex.org/W3094550259","https://openalex.org/W3112114674","https://openalex.org/W3119189689","https://openalex.org/W3160262112","https://openalex.org/W3205475937","https://openalex.org/W4226442948","https://openalex.org/W4294982636","https://openalex.org/W4296069160","https://openalex.org/W4296705186","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385823125","https://openalex.org/W4388117483","https://openalex.org/W4391859479","https://openalex.org/W4392903801","https://openalex.org/W4396877837","https://openalex.org/W4402111582","https://openalex.org/W4402774769","https://openalex.org/W6791353385","https://openalex.org/W6845479124","https://openalex.org/W6848208918","https://openalex.org/W6849109464","https://openalex.org/W6850002427","https://openalex.org/W6853754985","https://openalex.org/W6861505535","https://openalex.org/W6862734586"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,31,41,154],"unique":[3],"acoustic":[4,28],"sensing":[5],"devices":[6],"and":[7,20,44,97,107],"large-scale":[8],"audio":[9,77,86],"recognition":[10],"models":[11,25,66,79],"have":[12],"unlocked":[13],"new":[14,62],"possibilities":[15],"for":[16,60,68,125],"environmental":[17,155],"sound":[18,156],"monitoring":[19],"detection.":[21],"However,":[22],"applying":[23,99],"pretrained":[24],"to":[26,35,64,92,110,134,145],"non-conventional":[27,70],"sensors":[29,71],"results":[30],"performance":[32],"degradation":[33],"due":[34],"domain":[36,100],"shifts,":[37],"caused":[38],"by":[39,121],"differences":[40],"frequency":[42],"response":[43],"noise":[45,109],"characteristics":[46,113],"from":[47],"the":[48,94,112,115,135],"original":[49],"training":[50],"data.":[51],"In":[52],"this":[53,119],"study,":[54],"we":[55],"introduce":[56],"a":[57,147],"text-guided":[58],"framework":[59],"generating":[61,122],"datasets":[63,132],"retrain":[65],"specifically":[67],"these":[69],"efficiently.":[72],"Our":[73],"approach":[74],"integrates":[75],"text-conditional":[76],"generative":[78],"with":[80],"two":[81],"additional":[82],"steps:":[83],"(1)":[84],"selecting":[85],"samples":[87],"based":[88],"on":[89],"text":[90],"input":[91],"match":[93],"desired":[95],"sounds,":[96],"(2)":[98],"transfer":[101],"techniques":[102],"using":[103],"recorded":[104,136],"impulse":[105],"responses":[106],"background":[108],"simulate":[111],"of":[114],"sensors.":[116],"We":[117],"demonstrate":[118],"process":[120],"emulated":[123],"signals":[124,141],"fiber-optic":[126],"Distributed":[127],"Acoustic":[128],"Sensors":[129],"(DAS),":[130],"creating":[131],"similar":[133],"ESC-50":[137],"dataset.":[138],"The":[139],"generated":[140],"are":[142],"then":[143],"used":[144],"train":[146],"classifier,":[148],"which":[149],"outperforms":[150],"few-shot":[151],"learning":[152],"approaches":[153],"classification.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}