{"id":"https://openalex.org/W7108719205","doi":"https://doi.org/10.5281/zenodo.17811461","title":"Improving Neural Pitch Estimation with SWIPE Kernels","display_name":"Improving Neural Pitch Estimation with SWIPE Kernels","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108719205","doi":"https://doi.org/10.5281/zenodo.17811461"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811461","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811461","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811461","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"David Marttila","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Marttila","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Joshua D. Reiss","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joshua D. Reiss","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62794452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9269000291824341,"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":0.9269000291824341,"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":0.05249999836087227,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.005100000184029341,"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/swipe","display_name":"SwIPe","score":0.9559999704360962},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.680400013923645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6758000254631042},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.508899986743927},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.34139999747276306},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C2779623668","wikidata":"https://www.wikidata.org/wiki/Q7652842","display_name":"SwIPe","level":2,"score":0.9559999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523000240325928},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.680400013923645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6758000254631042},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.508899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49050000309944153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811461","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811461","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811461","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811461","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"networks":[1],"have":[2],"become":[3],"the":[4,32,43,88,95,111],"dominant":[5],"technique":[6],"for":[7,93],"accurate":[8,120],"pitch":[9,65,131],"and":[10,24,55,72,78,85,124],"periodicity":[11],"estimation.":[12],"Although":[13],"a":[14],"lot":[15],"of":[16,45,101],"research":[17],"has":[18],"gone":[19],"into":[20],"improving":[21],"network":[22,96],"architectures":[23,81],"training":[25],"paradigms,":[26],"most":[27],"approaches":[28],"operate":[29],"directly":[30],"on":[31,37,82,114],"raw":[33],"audio":[34,53,90],"waveform":[35],"or":[36],"general-purpose":[38],"time-frequency":[39],"representations.":[40],"We":[41,75],"investigate":[42],"use":[44],"Sawtooth-Inspired":[46],"Pitch":[47],"Estimation":[48],"(SWIPE)":[49],"kernels":[50],"as":[51],"an":[52,99],"frontend":[54,91],"find":[56],"that":[57,87,110,125],"these":[58],"hand-crafted,":[59],"task-specific":[60],"features":[61],"can":[62],"make":[63],"neural":[64,130],"estimators":[66,132],"more":[67,73,119],"accurate,":[68],"robust":[69],"to":[70],"noise,":[71],"parameter-efficient.":[74],"evaluate":[76],"supervised":[77],"self-supervised":[79,129],"state-of-the-art":[80,128],"common":[83],"datasets":[84],"show":[86,109],"SWIPE":[89,112],"allows":[92],"reducing":[94],"size":[97],"by":[98],"order":[100],"magnitude":[102],"without":[103],"any":[104],"performance":[105],"degradation.":[106],"Additionally,":[107],"we":[108],"algorithm":[113],"its":[115],"own":[116],"is":[117],"much":[118],"than":[121],"commonly":[122],"reported,":[123],"it":[126],"outperforms":[127],"when":[133],"properly":[134],"implemented.":[135]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}