{"id":"https://openalex.org/W4388691923","doi":"https://doi.org/10.1109/lsp.2023.3333205","title":"Multi-Scale Spectral Loss Revisited","display_name":"Multi-Scale Spectral Loss Revisited","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388691923","doi":"https://doi.org/10.1109/lsp.2023.3333205"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3333205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3333205","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10319088.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10319088.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073325105","display_name":"Simon Schw\u00e4r","orcid":"https://orcid.org/0000-0001-5780-557X"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simon Schw\u00e4r","raw_affiliation_strings":["International Audio Laboratories (a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS), Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories (a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories (a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS), Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories (a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073325105"],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":1.7829,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86267824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1712","last_page":"1716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/spectrogram","display_name":"Spectrogram","score":0.6473875045776367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6376535296440125},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5692576169967651},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5290022492408752},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.455486923456192},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.43778711557388306},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4320959448814392},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4122784733772278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3591139018535614},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.24935531616210938},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22649061679840088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21168231964111328}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6473875045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6376535296440125},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5692576169967651},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5290022492408752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.455486923456192},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.43778711557388306},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4320959448814392},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4122784733772278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3591139018535614},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.24935531616210938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22649061679840088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21168231964111328},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2023.3333205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3333205","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10319088.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/468985","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/468985","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"journal article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2023.3333205","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3333205","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10319088.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.75}],"awards":[{"id":"https://openalex.org/G3921662115","display_name":null,"funder_award_id":"DFG MU 2686/13-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388691923.pdf","grobid_xml":"https://content.openalex.org/works/W4388691923.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2336026683","https://openalex.org/W2480496932","https://openalex.org/W2606176153","https://openalex.org/W2962866891","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3165004824","https://openalex.org/W4238292067","https://openalex.org/W4316660651","https://openalex.org/W4323064860","https://openalex.org/W4372348434","https://openalex.org/W6714030504","https://openalex.org/W6736723571","https://openalex.org/W6746960179","https://openalex.org/W6771763809","https://openalex.org/W6784488536","https://openalex.org/W6787485125","https://openalex.org/W6842632288","https://openalex.org/W6842676699","https://openalex.org/W6846529734"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2566616303","https://openalex.org/W2011227383","https://openalex.org/W3131327266","https://openalex.org/W1976719989","https://openalex.org/W2942893872"],"abstract_inverted_index":{"The":[0,90],"Multi-Scale":[1],"Spectral":[2],"(MSS)":[3],"loss":[4,52,83,109,137,172],"is":[5,96,173],"commonly":[6],"used":[7],"for":[8],"comparing":[9],"audio":[10],"signals,":[11],"as":[12,34,36],"it":[13],"provides":[14],"a":[15,99,151,162],"good":[16],"trade-off":[17],"between":[18,39],"temporal":[19],"and":[20,30,54,132],"spectral":[21],"resolution.":[22],"However,":[23],"some":[24],"configuration":[25,164],"choices,":[26],"including":[27],"window":[28],"type":[29],"size,":[31],"magnitude":[32],"compression,":[33],"well":[35],"the":[37,51,55,62,76,81,107,119,136,170],"distance":[38],"spectrograms,":[40],"are":[41],"often":[42,84],"set":[43],"implicitly,":[44],"even":[45],"though":[46],"they":[47],"can":[48,145],"significantly":[49],"impact":[50],"properties":[53],"convergence":[56],"of":[57,64,78,93,102,106,121,150],"trained":[58],"models.":[59],"Particularly":[60],"in":[61],"context":[63],"differentiable":[65],"digital":[66],"signal":[67],"processing":[68],"(DDSP),":[69],"where":[70,169],"learned":[71],"parameters":[72],"may":[73,165],"explicitly":[74],"control":[75],"frequency":[77,123],"synthesis":[79,156],"components,":[80],"MSS":[82,108,171],"fails":[85],"to":[86,97,128],"provide":[87],"informative":[88],"gradients.":[89],"main":[91],"goal":[92],"this":[94,111],"paper":[95],"gain":[98],"better":[100],"understanding":[101],"how":[103],"different":[104,130],"configurations":[105,131,144],"affect":[110],"problem.":[112],"As":[113],"an":[114],"illustrative":[115],"example,":[116],"we":[117,140],"analyze":[118],"task":[120],"sinusoid":[122],"estimation":[124],"via":[125],"gradient":[126],"descent":[127],"compare":[129],"their":[133],"effect":[134],"on":[135],"properties.":[138],"Furthermore,":[139],"show":[141],"that":[142,161],"favorable":[143],"also":[146],"facilitate":[147],"unsupervised":[148],"training":[149],"more":[152],"complex":[153],"DDSP":[154],"additive":[155],"autoencoder.":[157],"Our":[158],"results":[159],"indicate":[160],"careful":[163],"benefit":[166],"many":[167],"applications":[168],"utilized.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}