{"id":"https://openalex.org/W2938603838","doi":"https://doi.org/10.1109/icassp.2019.8683199","title":"Embedding Physical Augmentation and Wavelet Scattering Transform to Generative Adversarial Networks for Audio Classification with Limited Training Resources","display_name":"Embedding Physical Augmentation and Wavelet Scattering Transform to Generative Adversarial Networks for Audio Classification with Limited Training Resources","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938603838","doi":"https://doi.org/10.1109/icassp.2019.8683199","mag":"2938603838"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5027076979","display_name":"Teh Kah Kuan","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Teh Kah Kuan","raw_affiliation_strings":["Acoustic, Speech and Language Department, Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustic, Speech and Language Department, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110125670","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Acoustic, Speech and Language Department, Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustic, Speech and Language Department, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3262","last_page":"3266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304434776306152},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6759325861930847},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5738404989242554},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5717761516571045},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.563032865524292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328401327133179},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5025622844696045},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4832794964313507},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4820598065853119},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46628260612487793},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4528723955154419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41921159625053406},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34959888458251953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30374592542648315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304434776306152},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6759325861930847},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5738404989242554},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5717761516571045},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.563032865524292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328401327133179},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5025622844696045},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4832794964313507},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4820598065853119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46628260612487793},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4528723955154419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41921159625053406},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34959888458251953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30374592542648315},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/icassp.2019.8683199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":37,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W1540630895","https://openalex.org/W1616590059","https://openalex.org/W1994906459","https://openalex.org/W2099471712","https://openalex.org/W2151484683","https://openalex.org/W2154579312","https://openalex.org/W2194775991","https://openalex.org/W2291864985","https://openalex.org/W2407080277","https://openalex.org/W2548275288","https://openalex.org/W2593116425","https://openalex.org/W2595120084","https://openalex.org/W2603142085","https://openalex.org/W2746993270","https://openalex.org/W2795050058","https://openalex.org/W2796876546","https://openalex.org/W2884013187","https://openalex.org/W2950776302","https://openalex.org/W2962756039","https://openalex.org/W2963373786","https://openalex.org/W2963971656","https://openalex.org/W2964187693","https://openalex.org/W4293665662","https://openalex.org/W4320013936","https://openalex.org/W6615969787","https://openalex.org/W6632377639","https://openalex.org/W6682751323","https://openalex.org/W6687483927","https://openalex.org/W6696764376","https://openalex.org/W6713762819","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6729831399","https://openalex.org/W6734260513","https://openalex.org/W6744040789","https://openalex.org/W6750326708"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"audio":[3],"classification":[4,68],"with":[5,61,89],"limited":[6,62],"training":[7,60,88,93],"resources.":[8,63],"We":[9,28],"first":[10],"investigate":[11],"different":[12],"types":[13],"of":[14,55,74],"data":[15],"augmentation":[16,38],"including":[17],"physical":[18,37],"modeling,":[19],"wavelet":[20,40],"scattering":[21,41],"transform":[22,42],"and":[23,39,76,85,91],"Generative":[24],"Adversarial":[25],"Networks":[26],"(GAN).":[27],"than":[29],"propose":[30],"a":[31],"novel":[32],"GAN":[33],"method":[34,58],"to":[35,80],"embed":[36],"in":[43],"processing.":[44],"The":[45],"experimental":[46],"results":[47],"on":[48,78],"Google":[49],"Speech":[50],"Command":[51],"show":[52],"significant":[53],"improvements":[54],"the":[56,71],"proposed":[57],"when":[59,87],"It":[64],"could":[65],"lift":[66],"up":[67],"accuracy":[69],"from":[70],"best":[72],"baselines":[73],"62.06%":[75],"77.29%":[77],"ResNet,":[79],"as":[81,83],"far":[82],"91.96%":[84],"93.38%,":[86],"10%":[90],"25%":[92],"data,":[94],"respectively.":[95]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}