{"id":"https://openalex.org/W4312445872","doi":"https://doi.org/10.1109/icwapr56446.2022.9947091","title":"The Scattering Transform Network with Generalized Morse Wavelets and its Application to Music Genre Classification","display_name":"The Scattering Transform Network with Generalized Morse Wavelets and its Application to Music Genre Classification","publication_year":2022,"publication_date":"2022-09-09","ids":{"openalex":"https://openalex.org/W4312445872","doi":"https://doi.org/10.1109/icwapr56446.2022.9947091"},"language":"en","primary_location":{"id":"doi:10.1109/icwapr56446.2022.9947091","doi":"https://doi.org/10.1109/icwapr56446.2022.9947091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icwapr56446.2022.9947091","pdf_url":null,"source":{"id":"https://openalex.org/S4306419913","display_name":"International Conference on Wavelet Analysis and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.07857","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041917766","display_name":"Wai Ho Chak","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wai Ho Chak","raw_affiliation_strings":["University of California,Graduate Group in Applied Mathematics,Davis,USA","Graduate Group in Applied Mathematics, University of California, Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Graduate Group in Applied Mathematics,Davis,USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Graduate Group in Applied Mathematics, University of California, Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067244173","display_name":"Naoki Saito","orcid":"https://orcid.org/0000-0001-5234-4719","observed_orcids":["https://orcid.org/0000-0001-5234-4719"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoki Saito","raw_affiliation_strings":["University of California,Graduate Group in Applied Mathematics,Davis,USA","Graduate Group in Applied Mathematics, University of California, Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Graduate Group in Applied Mathematics,Davis,USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Graduate Group in Applied Mathematics, University of California, Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Weber","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Weber","raw_affiliation_strings":["University of California,Graduate Group in Applied Mathematics,Davis,USA","Graduate Group in Applied Mathematics, University of California, Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Graduate Group in Applied Mathematics,Davis,USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Graduate Group in Applied Mathematics, University of California, Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":0.8657,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74368771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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":0.9932000041007996,"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/T11210","display_name":"Mathematical Analysis and Transform Methods","score":0.006099999882280827,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10220","display_name":"Machine Fault Diagnosis Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/morlet-wavelet","display_name":"Morlet wavelet","score":0.8550000190734863},{"id":"https://openalex.org/keywords/music-genre-classification","display_name":"music genre classification","score":0.972000002861023},{"id":"https://openalex.org/keywords/wavelet-filter-design","display_name":"wavelet filter design","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.7411242127418518},{"id":"https://openalex.org/C136902061","wikidata":"https://www.wikidata.org/wiki/Q16981559","display_name":"Gabor wavelet","level":5,"score":0.6609349250793457},{"id":"https://openalex.org/C2778280487","wikidata":"https://www.wikidata.org/wiki/Q3505077","display_name":"Morlet wavelet","level":5,"score":0.6206972599029541},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.48743441700935364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4564845561981201},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4382946789264679},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4143717885017395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.399972528219223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806638717651367},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.36609339714050293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3514571189880371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3381514251232147},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.3338651657104492},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2708160877227783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icwapr56446.2022.9947091","doi":"https://doi.org/10.1109/icwapr56446.2022.9947091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icwapr56446.2022.9947091","pdf_url":null,"source":{"id":"https://openalex.org/S4306419913","display_name":"International Conference on Wavelet Analysis and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.07857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07857","pdf_url":"https://arxiv.org/pdf/2206.07857","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.07857","doi":"https://doi.org/10.48550/arxiv.2206.07857","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.07857","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.07857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07857","pdf_url":"https://arxiv.org/pdf/2206.07857","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3069504102","display_name":"HDR TRIPODS: UC Davis TETRAPODS Institute of Data Science","funder_award_id":"1934568","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6249170234","display_name":"Flexible and Sound Computational Harmonic Analysis Tools for Graphs and Networks","funder_award_id":"1912747","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7947279504","display_name":null,"funder_award_id":"N00014-20-1-2381","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8006577219","display_name":null,"funder_award_id":"N00014-20","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312445872.pdf","grobid_xml":"https://content.openalex.org/works/W4312445872.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1994906459","https://openalex.org/W2003289302","https://openalex.org/W2072072671","https://openalex.org/W2080271204","https://openalex.org/W2120575449","https://openalex.org/W2133824856","https://openalex.org/W2137044549","https://openalex.org/W2159636559","https://openalex.org/W2166385084","https://openalex.org/W2196920785","https://openalex.org/W2919115771","https://openalex.org/W4302067267"],"related_works":["https://openalex.org/W6980833918","https://openalex.org/W4324290827","https://openalex.org/W4206040299","https://openalex.org/W2743665648","https://openalex.org/W1982043408","https://openalex.org/W24579641","https://openalex.org/W2076941229","https://openalex.org/W2264893961","https://openalex.org/W2626031595","https://openalex.org/W2998308282"],"abstract_inverted_index":{"We":[0,90],"propose":[1],"to":[2,125],"use":[3],"the":[4,17,25,42,56,74,92,95,98,106,113,117,128],"Generalized":[5],"Morse":[6],"Wavelets":[7],"(GMWs)":[8],"instead":[9],"of":[10,37,51,73,87,94,116,123],"commonly-used":[11],"Morlet":[12,43],"(or":[13],"Gabor)":[14],"wavelets":[15,40,44],"in":[16,55,101],"Scattering":[18],"Transform":[19],"Network":[20],"(STN),":[21],"which":[22],"we":[23,111],"call":[24],"GMW-STN,":[26],"for":[27,61],"signal":[28],"classification":[29,104],"problems.":[30],"The":[31,49],"GMWs":[32],"form":[33],"a":[34],"parameterized":[35],"family":[36],"truly":[38],"analytic":[39],"while":[41],"are":[45],"only":[46],"approximately":[47],"analytic.":[48],"analyticity":[50],"underlying":[52],"wavelet":[53],"filters":[54],"STN":[57,75,100],"is":[58],"particularly":[59],"important":[60],"nonstationary":[62],"oscillatory":[63],"signals":[64,68],"such":[65],"as":[66],"music":[67,102],"because":[69],"it":[70],"improves":[71],"interpretability":[72],"representations":[76],"by":[77,119],"providing":[78],"multi-scale":[79],"amplitude":[80],"and":[81],"phase":[82],"(and":[83],"consequently":[84],"frequency)":[85],"information":[86],"input":[88],"signals.":[89],"demonstrate":[91],"superiority":[93],"GMW-STN":[96,118],"over":[97,127],"conventional":[99],"genre":[103],"using":[105],"so-called":[107],"GTZAN":[108],"database.":[109],"Moreover,":[110],"show":[112],"performance":[114],"improvement":[115],"increasing":[120],"its":[121],"number":[122],"layers":[124],"three":[126],"typical":[129],"two-layer":[130],"STN.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-01-04T00:00:00"}