{"id":"https://openalex.org/W4392910576","doi":"https://doi.org/10.1109/icassp48485.2024.10446816","title":"DMEL: The Differentiable Log-Mel Spectrogram as a Trainable Layer in Neural Networks","display_name":"DMEL: The Differentiable Log-Mel Spectrogram as a Trainable Layer in Neural Networks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910576","doi":"https://doi.org/10.1109/icassp48485.2024.10446816"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5032224130","display_name":"John Martinsson","orcid":"https://orcid.org/0000-0002-5032-4367"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]},{"id":"https://openalex.org/I2800664555","display_name":"RISE Research Institutes of Sweden","ror":"https://ror.org/03nnxqz81","country_code":"SE","type":"other","lineage":["https://openalex.org/I2800664555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"John Martinsson","raw_affiliation_strings":["Lund University,Centre for Mathematical Sciences,Lund,Sweden","Centre for Mathematical Sciences, Lund University, Lund, Sweden","Computer Science, RISE Research Institutes of Sweden, Gothenburg, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University,Centre for Mathematical Sciences,Lund,Sweden","institution_ids":["https://openalex.org/I187531555"]},{"raw_affiliation_string":"Centre for Mathematical Sciences, Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]},{"raw_affiliation_string":"Computer Science, RISE Research Institutes of Sweden, Gothenburg, Sweden","institution_ids":["https://openalex.org/I2800664555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040600213","display_name":"Maria Sandsten","orcid":"https://orcid.org/0000-0002-8117-9588"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Maria Sandsten","raw_affiliation_strings":["Lund University,Centre for Mathematical Sciences,Lund,Sweden","Centre for Mathematical Sciences, Lund University, Lund, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University,Centre for Mathematical Sciences,Lund,Sweden","institution_ids":["https://openalex.org/I187531555"]},{"raw_affiliation_string":"Centre for Mathematical Sciences, Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]}],"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5005","last_page":"5009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9983000159263611,"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/T10320","display_name":"Neural Networks and Applications","score":0.9879999756813049,"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/spectrogram","display_name":"Spectrogram","score":0.8885941505432129},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7430126667022705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6665008068084717},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6583325862884521},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.6572127938270569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6352506875991821},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.579101026058197},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.449446439743042},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4363487660884857},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.42872336506843567},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.42314374446868896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38939008116722107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35751014947891235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3498454689979553},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2914869785308838}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8885941505432129},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7430126667022705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6665008068084717},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6583325862884521},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.6572127938270569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352506875991821},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.579101026058197},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.449446439743042},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4363487660884857},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.42872336506843567},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.42314374446868896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38939008116722107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35751014947891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3498454689979553},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2914869785308838},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:lup.lub.lu.se:32c15a29-82d8-4558-9537-0ece70f446fc","is_oa":false,"landing_page_url":"https://lup.lub.lu.se/record/32c15a29-82d8-4558-9537-0ece70f446fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306400536","display_name":"Lund University Publications (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1520-6149","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2038908859","https://openalex.org/W2052666245","https://openalex.org/W2188563164","https://openalex.org/W2872172641","https://openalex.org/W2962901777","https://openalex.org/W2963881567","https://openalex.org/W3094550259","https://openalex.org/W3097412542","https://openalex.org/W3196368020","https://openalex.org/W4211015359","https://openalex.org/W4297829726","https://openalex.org/W4312470705","https://openalex.org/W4312856903","https://openalex.org/W4312926530","https://openalex.org/W4372346630","https://openalex.org/W6753441104","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2056151855"],"abstract_inverted_index":{"In":[0,76],"this":[1],"paper":[2],"we":[3,78],"present":[4],"the":[5,28,35,63,80,115,120,127,131,140,144],"differentiable":[6,116],"log-Mel":[7],"spectrogram":[8,117,134],"(DMEL)":[9],"for":[10,58,99],"audio":[11,46],"classification.":[12],"DMEL":[13,31,51,84],"uses":[14],"a":[15,19,53,69,72,88,106],"Gaussian":[16],"window,":[17],"with":[18,27,71],"window":[20,64,74,94,122,146],"length":[21,65],"that":[22,50],"can":[23],"be":[24],"jointly":[25],"optimized":[26],"neural":[29,40],"network.":[30],"is":[32,110],"used":[33],"as":[34],"input":[36],"layer":[37],"in":[38],"different":[39,93],"networks":[41],"and":[42,85],"evaluated":[43],"on":[44,105,130],"standard":[45,89],"datasets.":[47],"We":[48,136],"show":[49],"achieves":[52],"higher":[54],"average":[55],"test":[56],"accuracy":[57],"sub-optimal":[59],"initial":[60],"choices":[61],"of":[62,83,126,133],"when":[66],"compared":[67],"to":[68,87,112,143],"baseline":[70],"fixed":[73],"length.":[75,123,147],"addition,":[77],"analyse":[79],"computational":[81],"cost":[82],"compare":[86],"hyperparameter":[90],"search":[91],"over":[92],"lengths,":[95],"showing":[96],"favorable":[97],"results":[98],"DMEL.":[100],"Finally,":[101],"an":[102],"empirical":[103],"evaluation":[104],"carefully":[107],"designed":[108],"dataset":[109,128],"performed":[111],"investigate":[113],"if":[114],"actually":[118],"learns":[119],"optimal":[121,145],"The":[124],"design":[125],"relies":[129],"theory":[132],"resolution.":[135],"also":[137],"empirically":[138],"evaluate":[139],"convergence":[141],"rate":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}