{"id":"https://openalex.org/W2034300186","doi":"https://doi.org/10.1109/taslp.2014.2363410","title":"Neural Network Based Pitch Tracking in Very Noisy Speech","display_name":"Neural Network Based Pitch Tracking in Very Noisy Speech","publication_year":2014,"publication_date":"2014-10-14","ids":{"openalex":"https://openalex.org/W2034300186","doi":"https://doi.org/10.1109/taslp.2014.2363410","mag":"2034300186"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2363410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2363410","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Han","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH"],"raw_orcid":"https://orcid.org/0000-0003-2148-7594","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":6.8948,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.97111778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"22","issue":"12","first_page":"2158","last_page":"2168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.7507503032684326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7009469866752625},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6179646253585815},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.6019898653030396},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5634452700614929},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5587455630302429},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5120483040809631},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49788784980773926},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4948243498802185},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.48267319798469543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4691319167613983},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45281782746315},{"id":"https://openalex.org/keywords/probabilistic-neural-network","display_name":"Probabilistic neural network","score":0.4351857304573059},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41336870193481445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37094348669052124},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.34464138746261597},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.326737642288208},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18477356433868408},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14878535270690918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507503032684326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7009469866752625},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6179646253585815},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.6019898653030396},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5634452700614929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5587455630302429},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5120483040809631},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49788784980773926},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4948243498802185},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.48267319798469543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4691319167613983},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45281782746315},{"id":"https://openalex.org/C134342201","wikidata":"https://www.wikidata.org/wiki/Q7246859","display_name":"Probabilistic neural network","level":4,"score":0.4351857304573059},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41336870193481445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37094348669052124},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.34464138746261597},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.326737642288208},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18477356433868408},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14878535270690918},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/taslp.2014.2363410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2363410","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W1498436455","https://openalex.org/W1886421314","https://openalex.org/W1974387177","https://openalex.org/W1984541135","https://openalex.org/W1990449877","https://openalex.org/W1993064527","https://openalex.org/W1993882792","https://openalex.org/W1995966271","https://openalex.org/W2004163116","https://openalex.org/W2013598660","https://openalex.org/W2013712815","https://openalex.org/W2027804983","https://openalex.org/W2045956438","https://openalex.org/W2052252043","https://openalex.org/W2057653135","https://openalex.org/W2064675550","https://openalex.org/W2085191029","https://openalex.org/W2091425152","https://openalex.org/W2100989275","https://openalex.org/W2103945478","https://openalex.org/W2110485445","https://openalex.org/W2115129089","https://openalex.org/W2115730999","https://openalex.org/W2119599673","https://openalex.org/W2122982914","https://openalex.org/W2125062731","https://openalex.org/W2130086727","https://openalex.org/W2135431242","https://openalex.org/W2136922672","https://openalex.org/W2142384583","https://openalex.org/W2144499799","https://openalex.org/W2147880316","https://openalex.org/W2149096369","https://openalex.org/W2159202424","https://openalex.org/W2163922914","https://openalex.org/W2168379380","https://openalex.org/W2252143850","https://openalex.org/W2290318471","https://openalex.org/W2981666567","https://openalex.org/W3216401400","https://openalex.org/W4254816979","https://openalex.org/W4285719527","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W1595652908","https://openalex.org/W2375446027","https://openalex.org/W2007798284","https://openalex.org/W2067837718","https://openalex.org/W2179098615","https://openalex.org/W1990055248","https://openalex.org/W2089093251","https://openalex.org/W38478948","https://openalex.org/W4385506173","https://openalex.org/W4294967761"],"abstract_inverted_index":{"Pitch":[0],"determination":[1],"is":[2,17,29,67,75,85,93],"a":[3,68,86],"fundamental":[4],"problem":[5],"in":[6,22],"speech":[7,50],"processing,":[8],"which":[9,74,92,116],"has":[10],"been":[11],"studied":[12],"for":[13],"decades.":[14],"However,":[15],"it":[16],"challenging":[18],"to":[19,138,147],"determinate":[20],"pitch":[21,36,43,59,114,121,133,158],"strong":[23],"noise":[24,140],"because":[25],"the":[26,41,131],"harmonic":[27],"structure":[28],"corrupted.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"estimate":[35],"using":[37],"supervised":[38],"learning,":[39],"where":[40],"probabilistic":[42,111],"states":[44],"are":[45,117,136],"directly":[46],"learned":[47],"from":[48],"noisy":[49],"data.":[51],"We":[52],"investigate":[53],"two":[54],"alternative":[55],"neural":[56,71,89],"networks":[57],"modeling":[58],"state":[60],"distribution":[61],"given":[62],"observations.":[63],"The":[64,82,150],"first":[65],"one":[66,84],"feedforward":[69],"deep":[70,88],"network":[72,90],"(DNN),":[73],"trained":[76,94],"on":[77,95],"static":[78],"frame-level":[79,97],"acoustic":[80],"features.":[81],"second":[83],"recurrent":[87],"(RNN)":[91],"sequential":[96],"features":[98],"and":[99,107,142],"capable":[100],"of":[101,113],"learning":[102],"temporal":[103],"dynamics.":[104],"Both":[105],"DNNs":[106],"RNNs":[108],"produce":[109],"accurate":[110],"outputs":[112],"states,":[115],"then":[118],"connected":[119],"into":[120],"contours":[122],"by":[123],"Viterbi":[124],"decoding.":[125],"Our":[126],"systematic":[127],"evaluation":[128],"shows":[129],"that":[130],"proposed":[132,151],"tracking":[134,159],"algorithms":[135],"robust":[137],"different":[139],"conditions":[141],"can":[143],"even":[144],"be":[145],"applied":[146],"reverberant":[148],"speech.":[149],"approach":[152],"also":[153],"significantly":[154],"outperforms":[155],"other":[156],"state-of-the-art":[157],"algorithms.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}