{"id":"https://openalex.org/W4375868780","doi":"https://doi.org/10.1109/icassp49357.2023.10095907","title":"Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond","display_name":"Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868780","doi":"https://doi.org/10.1109/icassp49357.2023.10095907"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035848608","display_name":"Ch. Wei\u00df","orcid":"https://orcid.org/0000-0003-2143-4679"},"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":"Christof Wei\u00df","raw_affiliation_strings":["International Audio Laboratories Erlangen"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"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":"1","last_page":"5"},"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":0.9986000061035156,"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":0.9776999950408936,"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":0.8074169158935547},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6956963539123535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6935077905654907},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5770741105079651},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5569180846214294},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5229314565658569},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.50987708568573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48470115661621094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4692293107509613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3762248754501343},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36879056692123413},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3407745659351349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1989521086215973}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8074169158935547},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6956963539123535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935077905654907},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5770741105079651},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5569180846214294},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5229314565658569},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.50987708568573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48470115661621094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4692293107509613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3762248754501343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36879056692123413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3407745659351349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1989521086215973},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1979654135","https://openalex.org/W2100816929","https://openalex.org/W2107328928","https://openalex.org/W2127141656","https://openalex.org/W2134096203","https://openalex.org/W2142927150","https://openalex.org/W2144414181","https://openalex.org/W2522234776","https://openalex.org/W2559688696","https://openalex.org/W2560254426","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2963405869","https://openalex.org/W2963642716","https://openalex.org/W2989787517","https://openalex.org/W3003566606","https://openalex.org/W3155085627","https://openalex.org/W3162528130","https://openalex.org/W3174257816","https://openalex.org/W3177098672","https://openalex.org/W3200791433","https://openalex.org/W4200250820","https://openalex.org/W4205501836","https://openalex.org/W4238292067","https://openalex.org/W4293775315","https://openalex.org/W6681102793","https://openalex.org/W6727014285","https://openalex.org/W6730401039","https://openalex.org/W6733936739","https://openalex.org/W6734312481","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6770639321","https://openalex.org/W6773854358"],"related_works":["https://openalex.org/W2145345839","https://openalex.org/W1487047144","https://openalex.org/W2614356544","https://openalex.org/W2267427430","https://openalex.org/W1545488252","https://openalex.org/W2116300362","https://openalex.org/W3164452386","https://openalex.org/W4330340085","https://openalex.org/W2546942002","https://openalex.org/W2462142965"],"abstract_inverted_index":{"Many":[0],"tasks":[1],"in":[2,107],"music":[3],"information":[4],"retrieval":[5],"(MIR)":[6],"involve":[7],"weakly":[8,33],"aligned":[9,34],"data,":[10],"where":[11],"exact":[12],"temporal":[13,19],"correspondences":[14],"are":[15],"unknown.":[16],"The":[17],"connectionist":[18],"classification":[20],"(CTC)":[21],"loss":[22],"is":[23,39],"a":[24,65,95],"standard":[25],"technique":[26],"to":[27,41,49,51,77,103,116],"learn":[28],"feature":[29],"representations":[30],"based":[31],"on":[32,92],"training":[35],"data.":[36],"However,":[37],"CTC":[38],"limited":[40],"discrete-valued":[42],"target":[43,118],"sequences":[44],"and":[45],"can":[46,71],"be":[47,72],"difficult":[48],"extend":[50],"multi-label":[52,97],"problems.":[53],"In":[54,101],"this":[55],"article,":[56],"we":[57,86],"show":[58,87],"how":[59],"soft":[60],"dynamic":[61],"time":[62],"warping":[63],"(SoftDTW),":[64],"differentiable":[66],"variant":[67],"of":[68,99,109],"classical":[69],"DTW,":[70],"used":[73],"as":[74,82],"an":[75,83],"alternative":[76],"CTC.":[78,100],"Using":[79],"multi-pitch":[80],"estimation":[81],"example":[84],"scenario,":[85],"that":[88],"SoftDTW":[89,113],"yields":[90],"results":[91],"par":[93],"with":[94],"state-of-the-art":[96],"extension":[98],"addition":[102],"being":[104],"more":[105],"elegant":[106],"terms":[108],"its":[110],"algorithmic":[111],"formulation,":[112],"naturally":[114],"extends":[115],"real-valued":[117],"sequences.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
