{"id":"https://openalex.org/W2956658377","doi":"https://doi.org/10.1109/icumt48472.2019.8970740","title":"Improving Machine Hearing on Limited Data Sets","display_name":"Improving Machine Hearing on Limited Data Sets","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2956658377","doi":"https://doi.org/10.1109/icumt48472.2019.8970740","mag":"2956658377"},"language":"en","primary_location":{"id":"doi:10.1109/icumt48472.2019.8970740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt48472.2019.8970740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.08950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058551081","display_name":"Pavol Har\u00e1r","orcid":"https://orcid.org/0000-0001-5206-1794"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Pavol Harar","raw_affiliation_strings":["Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","Univ of Vienna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Univ of Vienna","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019100770","display_name":"Roswitha Bammer","orcid":null},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roswitha Bammer","raw_affiliation_strings":["Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044865557","display_name":"Anna Breger","orcid":"https://orcid.org/0000-0001-8878-5743"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Anna Breger","raw_affiliation_strings":["Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056178266","display_name":"Monika D\u00f6rfler","orcid":"https://orcid.org/0000-0001-6139-630X"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Monika Dorfler","raw_affiliation_strings":["Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Faculty of Mathematics NuHAG, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027414361","display_name":"Zden\u011bk Sm\u00e9kal","orcid":"https://orcid.org/0000-0002-8483-5448"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zdenek Smekal","raw_affiliation_strings":["Department of Telecommunications, Brno University of Technology, Brno, Czech Republic","Brno University of Technology, Dept. of Telecommunications, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Dept. of Telecommunications, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0590801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9991000294685364,"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":0.9927999973297119,"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":0.897322416305542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076869249343872},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.594261109828949},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5815634727478027},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5647329092025757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5331816673278809},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5099414587020874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5083460211753845},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5074107050895691},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.496709406375885},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.49018675088882446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4773140847682953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34222280979156494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14066225290298462}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.897322416305542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076869249343872},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.594261109828949},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5815634727478027},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5647329092025757},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5331816673278809},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5099414587020874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5083460211753845},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5074107050895691},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.496709406375885},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.49018675088882446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4773140847682953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34222280979156494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14066225290298462},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icumt48472.2019.8970740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt48472.2019.8970740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.08950","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08950","pdf_url":"https://arxiv.org/pdf/1903.08950","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"},{"id":"mag:2956658377","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.08950v3","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.08950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.08950","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.08950","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08950","pdf_url":"https://arxiv.org/pdf/1903.08950","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G2916271932","display_name":"Computational harmonic analysis of high-dimensional biomedical data","funder_award_id":"VRG12-009","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"},{"id":"https://openalex.org/G7075013067","display_name":"Semantic Annotation by Learned Structured and Adaptive Signal Representations (SALSA)","funder_award_id":"MA14-018","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W206914897","https://openalex.org/W1522301498","https://openalex.org/W1605417594","https://openalex.org/W1766888123","https://openalex.org/W1849277567","https://openalex.org/W1878791236","https://openalex.org/W1928278792","https://openalex.org/W1994906459","https://openalex.org/W2046972719","https://openalex.org/W2093231248","https://openalex.org/W2120847449","https://openalex.org/W2235440302","https://openalex.org/W2261689926","https://openalex.org/W2733276039","https://openalex.org/W2767858146","https://openalex.org/W2797876989","https://openalex.org/W2962813390","https://openalex.org/W2963759070","https://openalex.org/W3005347330","https://openalex.org/W3103325175","https://openalex.org/W6631190155","https://openalex.org/W6639204139","https://openalex.org/W6740355095","https://openalex.org/W6751420435","https://openalex.org/W6753705079","https://openalex.org/W6786059930"],"related_works":["https://openalex.org/W3003766820","https://openalex.org/W2765532459","https://openalex.org/W3045302321","https://openalex.org/W2900801283","https://openalex.org/W2989819525","https://openalex.org/W3040811551","https://openalex.org/W3156684332","https://openalex.org/W3024840775","https://openalex.org/W2903799412","https://openalex.org/W3196974791","https://openalex.org/W2107229664","https://openalex.org/W2938486148","https://openalex.org/W3211665488","https://openalex.org/W2905649134","https://openalex.org/W2793088717","https://openalex.org/W2752238778","https://openalex.org/W2968682061","https://openalex.org/W2739619458","https://openalex.org/W3040620102","https://openalex.org/W2765507192"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"network":[2],"(CNN)":[3],"architectures":[4],"have":[5],"originated":[6],"and":[7,50,78,148,152,167],"revolutionized":[8],"machine":[9],"learning":[10],"for":[11,68,157],"images.":[12],"In":[13,71],"order":[14],"to":[15,34],"take":[16],"advantage":[17],"of":[18,59,64,85,114,159],"CNNs":[19],"in":[20,53,89,172],"predictive":[21],"modeling":[22],"with":[23,82,101],"audio":[24,38],"data,":[25],"standard":[26,98,139],"FFT-based":[27],"signal":[28],"processing":[29],"methods":[30,136],"are":[31,170],"often":[32],"applied":[33],"convert":[35],"the":[36,62,83,97,112,138],"raw":[37],"waveforms":[39],"into":[40],"an":[41,121,173],"image-like":[42],"representations":[43,80,118],"(e.g.":[44],"spectrograms).":[45],"Even":[46],"though":[47],"conventional":[48],"images":[49],"spectrograms":[51],"differ":[52],"their":[54,150],"feature":[55],"properties,":[56],"this":[57,72],"kind":[58],"pre-processing":[60],"reduces":[61],"amount":[63,84],"training":[65,87],"data":[66,88,117,146],"necessary":[67],"successful":[69],"training.":[70],"contribution":[73],"we":[74,110],"investigate":[75,111],"how":[76],"input":[77],"target":[79,116,123],"interplay":[81],"available":[86,129,171],"a":[90,102,144],"music":[91],"information":[92],"retrieval":[93],"setting.":[94],"We":[95,131],"compare":[96],"mel-spectrogram":[99],"inputs":[100],"newly":[103],"proposed":[104,135],"representation,":[105],"called":[106],"Mel":[107],"scattering.":[108],"Furthermore,":[109],"impact":[113],"additional":[115],"by":[119],"using":[120,143],"augmented":[122],"loss":[124],"function":[125],"which":[126],"incorporates":[127],"unused":[128],"information.":[130],"observe":[132],"that":[133],"all":[134],"outperform":[137],"mel-transform":[140],"representation":[141],"when":[142],"limited":[145],"set":[147],"discuss":[149],"strengths":[151],"limitations.":[153],"The":[154],"source":[155],"code":[156],"reproducibility":[158],"our":[160],"experiments":[161],"as":[162,164],"well":[163],"intermediate":[165],"results":[166],"model":[168],"checkpoints":[169],"online":[174],"repository.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}