{"id":"https://openalex.org/W2963470561","doi":"https://doi.org/10.21437/odyssey.2018-39","title":"A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech","display_name":"A Regression Model of Recurrent Deep Neural Networks for Noise Robust Estimation of the Fundamental Frequency Contour of Speech","publication_year":2018,"publication_date":"2018-06-06","ids":{"openalex":"https://openalex.org/W2963470561","doi":"https://doi.org/10.21437/odyssey.2018-39","mag":"2963470561"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2018-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","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/A5059038393","display_name":"Akihiro Kato","orcid":"https://orcid.org/0000-0002-5796-2310"},"institutions":[{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Akihiro Kato","raw_affiliation_strings":["School of Computing University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059038393"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"],"apc_list":null,"apc_paid":null,"fwci":0.6634,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71819488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7334307432174683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7146340608596802},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6265167593955994},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.616131603717804},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5843376517295837},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5253388285636902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187733173370361},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5008077621459961},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4469006061553955},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.4344231188297272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4335799813270569},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4323870539665222},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41306668519973755},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13541710376739502},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11473298072814941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334307432174683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7146340608596802},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6265167593955994},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.616131603717804},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5843376517295837},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5253388285636902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187733173370361},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5008077621459961},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4469006061553955},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.4344231188297272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4335799813270569},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4323870539665222},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41306668519973755},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13541710376739502},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11473298072814941},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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:10.21437/odyssey.2018-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1974387177","https://openalex.org/W1990449877","https://openalex.org/W2013712815","https://openalex.org/W2034300186","https://openalex.org/W2062227835","https://openalex.org/W2078528584","https://openalex.org/W2088632109","https://openalex.org/W2091425152","https://openalex.org/W2102003408","https://openalex.org/W2115129089","https://openalex.org/W2118740006","https://openalex.org/W2124173482","https://openalex.org/W2147768505","https://openalex.org/W2157867825","https://openalex.org/W2160815625","https://openalex.org/W2163614729","https://openalex.org/W2304609584","https://openalex.org/W2305896111","https://openalex.org/W2325324198","https://openalex.org/W2327501763","https://openalex.org/W2395043875","https://openalex.org/W2403891086","https://openalex.org/W2404934284","https://openalex.org/W2433826538","https://openalex.org/W2516301810","https://openalex.org/W2517670980","https://openalex.org/W2576309025","https://openalex.org/W2588301167","https://openalex.org/W2635922319","https://openalex.org/W2747914378","https://openalex.org/W2748900478","https://openalex.org/W2748979424","https://openalex.org/W2766736793"],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W2145654520","https://openalex.org/W2750037515"],"abstract_inverted_index":{"The":[0],"fundamental":[1],"frequency":[2,118],"(F":[3],"0)":[4],"contour":[5,48],"of":[6,49,70,161],"speech":[7,14,20,30,50],"is":[8,176],"a":[9,82,105,183],"key":[10],"aspect":[11],"to":[12,43,111],"represent":[13],"prosody":[15],"that":[16],"finds":[17],"use":[18],"in":[19,109],"and":[21,29,36,56,122,154],"spoken":[22],"language":[23,37],"analysis":[24],"such":[25],"as":[26,32,34,81,104,157],"voice":[27],"conversion":[28],"synthesis":[31],"well":[33],"speaker":[35],"identification.This":[38],"work":[39],"proposes":[40],"new":[41],"methods":[42],"estimate":[44],"the":[45,67,102,134,162,169],"F":[46,71,113,165],"0":[47,72,114,166],"using":[51,63,89,125],"deep":[52,90],"neural":[53,58,91],"networks":[54,59],"(DNNs)":[55],"recurrent":[57],"(RNNs).They":[60],"are":[61],"trained":[62],"supervised":[64],"learning":[65],"with":[66,116,129,159],"ground":[68],"truth":[69],"contours.The":[73],"latest":[74],"prior":[75],"research":[76],"addresses":[77],"this":[78],"problem":[79,84,103,107],"first":[80],"frame-byframe-classification":[83],"followed":[85],"by":[86,142,178],"sequence":[87],"tracking":[88],"network":[92],"hidden":[93],"Markov":[94],"model":[95],"(DNN-HMM)":[96],"hybrid":[97],"architecture.This":[98],"study,":[99],"however,":[100],"tackles":[101],"regression":[106],"instead,":[108],"order":[110],"obtain":[112],"contours":[115],"higher":[117],"resolution":[119],"from":[120],"clean":[121],"noisy":[123],"speech.Experiments":[124],"PTDB-TUG":[126],"corpus":[127],"contaminated":[128],"additive":[130],"noise":[131],"(NOISEX-92)":[132],"show":[133],"proposed":[135],"method":[136],"improves":[137],"gross":[138],"pitch":[139,173],"error":[140,174],"(GPE)":[141],"more":[143],"than":[144],"25":[145],"%":[146,181],"at":[147],"signal-tonoise":[148],"ratios":[149],"(SNRs)":[150],"between":[151],"-10":[152],"dB":[153,156],"+10":[155],"compared":[158],"one":[160],"most":[163],"noise-robust":[164],"trackers,":[167],"PEFAC.Furthermore,":[168],"performance":[170],"on":[171],"fine":[172],"(FPE)":[175],"improved":[177],"approximately":[179],"20":[180],"against":[182],"state-of-the-art":[184],"DNN-HMMbased":[185],"approach.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}