{"id":"https://openalex.org/W2002850343","doi":"https://doi.org/10.1109/mlsp.2015.7324385","title":"Joint time-frequency scattering for audio classification","display_name":"Joint time-frequency scattering for audio classification","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2002850343","doi":"https://doi.org/10.1109/mlsp.2015.7324385","mag":"2002850343"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1512.02125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043290570","display_name":"Joakim And\u00e9n","orcid":"https://orcid.org/0000-0002-3377-813X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joakim Anden","raw_affiliation_strings":["PACM Princeton University, Princeton, NJ, USA","PACM, Princeton Univ., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"PACM Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"PACM, Princeton Univ., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027789239","display_name":"Vincent Lostanlen","orcid":"https://orcid.org/0000-0003-0580-1651"},"institutions":[{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]},{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Lostanlen","raw_affiliation_strings":["D\u00e9partement d'Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","D\u00e9partement d\u2019Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France"],"affiliations":[{"raw_affiliation_string":"D\u00e9partement d'Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]},{"raw_affiliation_string":"D\u00e9partement d\u2019Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065086376","display_name":"St\u00e9phane Mallat","orcid":"https://orcid.org/0000-0001-5263-8960"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210161954","display_name":"D\u00e9partement d'Informatique","ror":"https://ror.org/05y6rqs46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210159245","https://openalex.org/I4210161954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stephane Mallat","raw_affiliation_strings":["D\u00e9partement d'Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","D\u00e9partement d\u2019Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France"],"affiliations":[{"raw_affiliation_string":"D\u00e9partement d'Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]},{"raw_affiliation_string":"D\u00e9partement d\u2019Informatique, \u00c9cole normale sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210161954"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043290570"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":3.1836,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92407971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9926999807357788,"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/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.7620624899864197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6397019624710083},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.6153957843780518},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.596150279045105},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5816080570220947},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5659369826316833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5443368554115295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138561725616455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4973786175251007},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4459555149078369},{"id":"https://openalex.org/keywords/continuous-wavelet-transform","display_name":"Continuous wavelet transform","score":0.4432050287723541},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.4175024628639221},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.24424028396606445},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1915733516216278},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.17726874351501465},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.10121583938598633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08375024795532227}],"concepts":[{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.7620624899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6397019624710083},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.6153957843780518},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.596150279045105},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5816080570220947},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5659369826316833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5443368554115295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138561725616455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4973786175251007},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4459555149078369},{"id":"https://openalex.org/C95722684","wikidata":"https://www.wikidata.org/wiki/Q2622756","display_name":"Continuous wavelet transform","level":5,"score":0.4432050287723541},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.4175024628639221},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.24424028396606445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1915733516216278},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.17726874351501465},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.10121583938598633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08375024795532227},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp.2015.7324385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1512.02125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.02125","pdf_url":"https://arxiv.org/pdf/1512.02125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1512.02125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1512.02125","pdf_url":"https://arxiv.org/pdf/1512.02125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W9692546","https://openalex.org/W1641465689","https://openalex.org/W1994906459","https://openalex.org/W2015861736","https://openalex.org/W2054139811","https://openalex.org/W2062663442","https://openalex.org/W2093231248","https://openalex.org/W2107157326","https://openalex.org/W2107789863","https://openalex.org/W2130426352","https://openalex.org/W2131870124","https://openalex.org/W2148154194","https://openalex.org/W2153635508","https://openalex.org/W3120421331","https://openalex.org/W4245923654","https://openalex.org/W6600365384","https://openalex.org/W6636832325","https://openalex.org/W6676071220","https://openalex.org/W6679579573"],"related_works":["https://openalex.org/W1947057263","https://openalex.org/W2355447608","https://openalex.org/W1980067354","https://openalex.org/W2990382479","https://openalex.org/W1978333447","https://openalex.org/W2033324903","https://openalex.org/W1963506688","https://openalex.org/W2249701588","https://openalex.org/W2166544541","https://openalex.org/W4383502298"],"abstract_inverted_index":{"We":[0,36],"introduce":[1],"the":[2,66],"joint":[3],"time-frequency":[4,13,33,44],"scattering":[5],"transform,":[6],"a":[7,23,32],"time":[8,28],"shift":[9],"invariant":[10],"descriptor":[11,40],"of":[12],"structure":[14],"for":[15,58],"audio":[16],"classification.":[17],"It":[18],"is":[19],"obtained":[20],"by":[21],"applying":[22],"two-dimensional":[24],"wavelet":[25,34],"transform":[26],"in":[27],"and":[29,50,61],"log-frequency":[30],"to":[31],"scalogram.":[35],"show":[37],"that":[38],"this":[39],"successfully":[41],"characterizes":[42],"complex":[43],"phenomena":[45],"such":[46],"as":[47],"time-varying":[48],"filters":[49],"frequency":[51],"modulated":[52],"excitations.":[53],"State-of-the-art":[54],"results":[55],"are":[56],"achieved":[57],"signal":[59],"reconstruction":[60],"phone":[62],"segment":[63],"classification":[64],"on":[65],"TIMIT":[67],"dataset.":[68]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2016-06-24T00:00:00"}