{"id":"https://openalex.org/W4408354686","doi":"https://doi.org/10.1109/icassp49660.2025.10888824","title":"Wavelet Scattering Network Features for Intensity Category Classification and Prediction of SPL from Speech","display_name":"Wavelet Scattering Network Features for Intensity Category Classification and Prediction of SPL from Speech","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354686","doi":"https://doi.org/10.1109/icassp49660.2025.10888824"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888824","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":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/a9096bbc-1e88-40a2-ad63-6dedb6fdc19a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042157833","display_name":"Manila Kodali","orcid":"https://orcid.org/0000-0003-4594-4921"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manila Kodali","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4557,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83044933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9351000189781189,"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":0.9351000189781189,"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":0.682243824005127},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6503722667694092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5612058639526367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5436825156211853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5031904578208923},{"id":"https://openalex.org/keywords/intensity","display_name":"Intensity (physics)","score":0.48033395409584045},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.4170651137828827},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0725233256816864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682243824005127},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6503722667694092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612058639526367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5436825156211853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5031904578208923},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.48033395409584045},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.4170651137828827},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0725233256816864},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888824","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"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/135695","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/a9096bbc-1e88-40a2-ad63-6dedb6fdc19a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/135695","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/a9096bbc-1e88-40a2-ad63-6dedb6fdc19a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W177407077","https://openalex.org/W1981529741","https://openalex.org/W1994906459","https://openalex.org/W2009179928","https://openalex.org/W2025386793","https://openalex.org/W2043039711","https://openalex.org/W2046331056","https://openalex.org/W2054139811","https://openalex.org/W2080240461","https://openalex.org/W2093231248","https://openalex.org/W2125514156","https://openalex.org/W2155517073","https://openalex.org/W2239141610","https://openalex.org/W2261689926","https://openalex.org/W2401969501","https://openalex.org/W2404938947","https://openalex.org/W2787946070","https://openalex.org/W3007267003","https://openalex.org/W3197903945","https://openalex.org/W4205643594","https://openalex.org/W4292262097","https://openalex.org/W4385823457","https://openalex.org/W4390636217","https://openalex.org/W4391131509","https://openalex.org/W4391281089","https://openalex.org/W4399433813","https://openalex.org/W4402112313","https://openalex.org/W6863039576"],"related_works":["https://openalex.org/W2382174632","https://openalex.org/W2129959498","https://openalex.org/W2784060934","https://openalex.org/W2902714807","https://openalex.org/W2537489131","https://openalex.org/W2046633342","https://openalex.org/W2394084632","https://openalex.org/W2358293514","https://openalex.org/W2059273319","https://openalex.org/W2077021924"],"abstract_inverted_index":{"Speakers":[0],"change":[1],"vocal":[2,15,64],"intensity":[3,22,34,45,65,114],"in":[4,54,93,105],"daily":[5],"life":[6],"to":[7,13,145,167],"communicate":[8],"over":[9],"long":[10],"distances":[11],"and":[12,27,30,68,82,124],"express":[14],"emotions.":[16],"Humans":[17],"produce":[18],"speech":[19,51,91,111],"using":[20],"different":[21],"categories":[23,115],"(e.g.":[24],"soft,":[25],"normal":[26],"loud":[28],"voice)":[29],"they":[31],"can":[32],"regulate":[33],"across":[35],"a":[36],"wide":[37],"sound":[38],"pressure":[39],"level":[40],"(SPL)":[41],"range.":[42],"Knowing":[43],"the":[44,48,63,99,132,135,149,152,156,168],"category":[46,66],"or":[47],"SPL":[49,71,79,128,159],"of":[50,57,70,110,127,142,158,163],"is":[52,83],"beneficial":[53],"speech-based":[55],"biomarking":[56],"health.":[58],"Recent":[59],"studies":[60],"have":[61],"explored":[62],"classification":[67,109,122],"prediction":[69,126,157],"from":[72],"speech,":[73],"which":[74],"has":[75],"been":[76],"recorded":[77],"without":[78],"calibration":[80],"information":[81],"presented":[84],"on":[85],"an":[86,161],"arbitrary":[87],"amplitude":[88],"scale.":[89],"Using":[90],"signals":[92],"such":[94],"scenario,":[95],"this":[96],"study":[97],"investigates":[98],"wavelet":[100],"scattering":[101],"network":[102],"(WSN)":[103],"features":[104,137,154],"two":[106],"tasks:":[107],"(1)":[108],"into":[112],"four":[113],"(soft,":[116],"normal,":[117],"loud,":[118],"very":[119],"loud)":[120],"(multi-class":[121],"task)":[123],"(2)":[125],"(regression":[129],"task).":[130],"In":[131],"former":[133],"task,":[134,151],"WSN":[136,153],"showed":[138],"absolute":[139],"accuracy":[140],"improvements":[141],"4-14%":[143],"compared":[144,166],"reference":[146,169],"features.":[147,170],"For":[148],"latter":[150],"improved":[155],"by":[160],"average":[162],"1-2":[164],"dB":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}