{"id":"https://openalex.org/W4392904496","doi":"https://doi.org/10.1109/icassp48485.2024.10446578","title":"Soft Dynamic Time Warping with Variable Step Weights","display_name":"Soft Dynamic Time Warping with Variable Step Weights","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904496","doi":"https://doi.org/10.1109/icassp48485.2024.10446578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446578","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":"article","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/A5032789917","display_name":"Johannes Zeitler","orcid":"https://orcid.org/0000-0003-2171-7679"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Zeitler","raw_affiliation_strings":["International Audio Laboratories Erlangen"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061519162","display_name":"Michael Krause","orcid":"https://orcid.org/0000-0001-7194-0719"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Krause","raw_affiliation_strings":["International Audio Laboratories Erlangen"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","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 Erlangen"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032789917"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":1.3662,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79101314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9975000023841858,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8148889541625977},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7475797533988953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261410355567932},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.702450156211853},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6407787799835205},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5825258493423462},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5775228142738342},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5489856600761414},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5414602160453796},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5166890621185303},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5001440048217773},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4919392764568329},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4136582612991333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4090663194656372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34202274680137634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19305911660194397}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8148889541625977},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7475797533988953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261410355567932},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.702450156211853},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6407787799835205},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5825258493423462},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5775228142738342},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5489856600761414},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5414602160453796},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5166890621185303},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5001440048217773},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4919392764568329},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4136582612991333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090663194656372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34202274680137634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19305911660194397},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446578","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2627255612","display_name":"\u00dfThymosine, Substrat von Transglutaminasen bei Blutgerinnung und Apoptose","funder_award_id":"5214206","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4312340041","display_name":"Differenzierbare Alignierungstechniken f\u00fcr Music Information Retrieval","funder_award_id":"521420645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5748569654","display_name":null,"funder_award_id":"MU 2686/7-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G803975870","display_name":"Computergest\u00fctzte Analyse harmonischer Strukturen","funder_award_id":"252013209","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1490430289","https://openalex.org/W1980497326","https://openalex.org/W2127141656","https://openalex.org/W2139106564","https://openalex.org/W2906214917","https://openalex.org/W2917340025","https://openalex.org/W2963642716","https://openalex.org/W3003566606","https://openalex.org/W3162528130","https://openalex.org/W3177098672","https://openalex.org/W3196426375","https://openalex.org/W3197988356","https://openalex.org/W4200250820","https://openalex.org/W4200632724","https://openalex.org/W4205501836","https://openalex.org/W4238292067","https://openalex.org/W4286859126","https://openalex.org/W4375868780","https://openalex.org/W6675365184","https://openalex.org/W6734312481","https://openalex.org/W6747989175","https://openalex.org/W6784591980","https://openalex.org/W6800512119","https://openalex.org/W6855769626"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2347413598","https://openalex.org/W2330863229","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2350336482","https://openalex.org/W2362065912","https://openalex.org/W2367646230","https://openalex.org/W2353445236","https://openalex.org/W62023843"],"abstract_inverted_index":{"In":[0,30,105],"computer":[1],"vision":[2],"and":[3,37,93,117,126],"audio":[4],"processing,":[5],"soft":[6],"dynamic":[7,120],"time":[8],"warping":[9],"(SDTW)":[10],"techniques":[11],"have":[12,42,94],"been":[13,95],"used":[14],"as":[15],"a":[16,73,144],"differentiable":[17],"loss":[18],"function":[19],"to":[20,50,64,72,101,111],"train":[21],"deep":[22],"neural":[23],"networks":[24],"(DNNs)":[25],"on":[26,139],"weakly":[27],"aligned":[28],"data.":[29],"existing":[31],"SDTW":[32,110],"algorithms,":[33],"the":[34,43,51,78,124,134,137,140,159,166],"horizontal,":[35],"vertical,":[36],"diagonal":[38],"alignment":[39,52],"steps":[40],"all":[41,59],"same":[44,167],"weight,":[45],"i.e.,":[46],"they":[47],"contribute":[48],"equally":[49],"cost.":[53],"This":[54],"equal":[55,85],"weighting":[56],"scheme":[57],"for":[58,113,123,146],"step":[60,86,103,115,154],"sizes":[61],"can":[62],"lead":[63],"degenerated":[65],"alignments":[66],"by,":[67],"e.g.,":[68],"aligning":[69],"most":[70],"predictions":[71],"single":[74],"target":[75,168],"frame":[76],"in":[77,163],"early":[79],"stages":[80],"of":[81,136,142,161,165],"training.":[82],"Problems":[83],"with":[84],"weights":[87,100,116],"are":[88],"known":[89],"from":[90,150],"classical":[91],"DTW":[92],"addressed":[96],"by":[97],"assigning":[98],"different":[99,102],"sizes.":[104],"this":[106],"paper,":[107],"we":[108,132],"extend":[109],"allow":[112],"variable":[114],"provide":[118],"efficient":[119],"programming":[121],"algorithms":[122],"forward":[125],"backward":[127],"passes.":[128],"As":[129],"an":[130],"example,":[131],"demonstrate":[133],"potential":[135],"method":[138],"task":[141],"training":[143],"DNN":[145],"pitch":[147],"class":[148],"estimation":[149],"music":[151],"recordings,":[152],"using":[153],"weight":[155],"parameters":[156],"that":[157],"reduce":[158],"influence":[160],"outliers":[162],"repetitions":[164],"frame.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}