{"id":"https://openalex.org/W3161758688","doi":"https://doi.org/10.1109/icassp39728.2021.9414050","title":"DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals","display_name":"DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161758688","doi":"https://doi.org/10.1109/icassp39728.2021.9414050","mag":"3161758688"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5070580244","display_name":"Satwinder Singh","orcid":"https://orcid.org/0000-0001-9032-6781"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Satwinder Singh","raw_affiliation_strings":["School of Natural and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Natural and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694558","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0001-7117-2772"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["School of Natural and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Natural and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000331282","display_name":"Yuanhang Qiu","orcid":"https://orcid.org/0000-0002-3015-6829"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yuanhang Qiu","raw_affiliation_strings":["School of Natural and Computational Sciences, Massey University, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Natural and Computational Sciences, Massey University, Auckland, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51158804"],"apc_list":null,"apc_paid":null,"fwci":3.8071,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95485919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"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":0.9995999932289124,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957826852798462},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6879023313522339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5577749609947205},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5080230236053467},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4808686375617981},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.47247880697250366},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4670848846435547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45840221643447876},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4477958381175995},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.44459208846092224},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43661922216415405},{"id":"https://openalex.org/keywords/dilation","display_name":"Dilation (metric space)","score":0.42668431997299194},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21113157272338867},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15226608514785767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1060575544834137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957826852798462},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6879023313522339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5577749609947205},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5080230236053467},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4808686375617981},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.47247880697250366},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4670848846435547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45840221643447876},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4477958381175995},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.44459208846092224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43661922216415405},{"id":"https://openalex.org/C2780757906","wikidata":"https://www.wikidata.org/wiki/Q5276676","display_name":"Dilation (metric space)","level":2,"score":0.42668431997299194},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21113157272338867},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15226608514785767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1060575544834137},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1975079546","https://openalex.org/W1990449877","https://openalex.org/W2034300186","https://openalex.org/W2085628288","https://openalex.org/W2091425152","https://openalex.org/W2107328928","https://openalex.org/W2118774185","https://openalex.org/W2124539664","https://openalex.org/W2147634797","https://openalex.org/W2188267022","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2296724634","https://openalex.org/W2398826216","https://openalex.org/W2403891086","https://openalex.org/W2407685581","https://openalex.org/W2516301810","https://openalex.org/W2519091744","https://openalex.org/W2606176153","https://openalex.org/W2774581901","https://openalex.org/W2792764867","https://openalex.org/W2914095411","https://openalex.org/W2932319787","https://openalex.org/W2949382160","https://openalex.org/W2962866891","https://openalex.org/W2963685250","https://openalex.org/W2964121744","https://openalex.org/W2972353749","https://openalex.org/W2980121906","https://openalex.org/W3011176162","https://openalex.org/W3095789485","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6672028191","https://openalex.org/W6677920165","https://openalex.org/W6678626330","https://openalex.org/W6687133601","https://openalex.org/W6695676441","https://openalex.org/W6697040288","https://openalex.org/W6712560600","https://openalex.org/W6713478990","https://openalex.org/W6714030504","https://openalex.org/W6736723571","https://openalex.org/W6746960179","https://openalex.org/W6748253163","https://openalex.org/W6749825310"],"related_works":["https://openalex.org/W2079003682","https://openalex.org/W2089544495","https://openalex.org/W2913266608","https://openalex.org/W1555021777","https://openalex.org/W1970258141","https://openalex.org/W2799648451","https://openalex.org/W1964918325","https://openalex.org/W2189496153","https://openalex.org/W2186491718","https://openalex.org/W2034008118"],"abstract_inverted_index":{"We":[0,141],"propose":[1],"a":[2,23,68],"novel":[3],"pitch":[4,43,129,151],"estimation":[5,152],"technique":[6],"called":[7],"DeepF0,":[8],"which":[9],"leverages":[10],"the":[11,19,64,72,77,83,90,93,98,119,123,155],"available":[12],"annotated":[13],"data":[14],"to":[15,51],"directly":[16],"learns":[17],"from":[18],"raw":[20,128,132],"audio":[21],"in":[22,29,125],"data-driven":[24],"manner.":[25],"f0estimation":[26],"is":[27,106],"important":[28],"various":[30,156],"speech":[31],"processing":[32],"and":[33,103,131],"music":[34],"information":[35],"retrieval":[36],"applications.":[37],"Existing":[38],"deep":[39],"learning":[40,48],"models":[41],"for":[42],"estimations":[44],"have":[45],"relatively":[46],"limited":[47],"capabilities":[49],"due":[50],"their":[52],"shallow":[53],"receptive":[54,65,85],"field.":[55],"The":[56,79],"proposed":[57,120],"model":[58,94,121,146],"addresses":[59],"this":[60],"issue":[61],"by":[62,70],"extending":[63],"field":[66,86],"of":[67,92,127,158],"network":[69,84,139],"introducing":[71],"dilated":[73],"convolutional":[74],"blocks":[75,110],"into":[76],"network.":[78],"dilation":[80],"factor":[81],"increases":[82],"exponentially":[87],"without":[88],"increasing":[89],"parameters":[91],"exponentially.":[95],"To":[96],"make":[97],"training":[99],"process":[100],"more":[101],"efficient":[102],"faster,":[104],"DeepF0":[105],"augmented":[107],"with":[108,111],"residual":[109,112],"connections.":[113],"Our":[114],"empirical":[115],"evaluation":[116],"demonstrates":[117],"that":[118,144],"outperforms":[122],"baselines":[124],"terms":[126],"accuracy":[130,134],"chroma":[133],"even":[135,153],"using":[136],"77.4%":[137],"fewer":[138],"parameters.":[140],"also":[142],"show":[143],"our":[145],"can":[147],"capture":[148],"reasonably":[149],"well":[150],"under":[154],"levels":[157],"accompaniment":[159],"noise.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}