{"id":"https://openalex.org/W2013712815","doi":"https://doi.org/10.1109/icassp.2014.6853845","title":"Neural networks for supervised pitch tracking in noise","display_name":"Neural networks for supervised pitch tracking in noise","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2013712815","doi":"https://doi.org/10.1109/icassp.2014.6853845","mag":"2013712815"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/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, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","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, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","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":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"495","issue":null,"first_page":"1488","last_page":"1492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.7565321922302246},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6534909009933472},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6412758231163025},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6110628843307495},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5803513526916504},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5740921497344971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5619530081748962},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5059649348258972},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48041605949401855},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4755256474018097},{"id":"https://openalex.org/keywords/probabilistic-neural-network","display_name":"Probabilistic neural network","score":0.47463998198509216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44829443097114563},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44359055161476135},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.43274006247520447},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42905157804489136},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.41594773530960083},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.35235586762428284},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.31421926617622375},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3019852638244629},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11300963163375854},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08526402711868286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565321922302246},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6534909009933472},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6412758231163025},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6110628843307495},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5803513526916504},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5740921497344971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619530081748962},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5059649348258972},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48041605949401855},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4755256474018097},{"id":"https://openalex.org/C134342201","wikidata":"https://www.wikidata.org/wiki/Q7246859","display_name":"Probabilistic neural network","level":4,"score":0.47463998198509216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44829443097114563},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44359055161476135},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.43274006247520447},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42905157804489136},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.41594773530960083},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.35235586762428284},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31421926617622375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3019852638244629},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11300963163375854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08526402711868286},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/icassp.2014.6853845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W1571821784","https://openalex.org/W1974387177","https://openalex.org/W1993064527","https://openalex.org/W1993882792","https://openalex.org/W2004163116","https://openalex.org/W2045956438","https://openalex.org/W2052252043","https://openalex.org/W2061140267","https://openalex.org/W2085191029","https://openalex.org/W2091425152","https://openalex.org/W2100989275","https://openalex.org/W2115129089","https://openalex.org/W2115730999","https://openalex.org/W2119599673","https://openalex.org/W2135431242","https://openalex.org/W2136922672","https://openalex.org/W2142384583","https://openalex.org/W2168379380","https://openalex.org/W2290318471","https://openalex.org/W2981666567","https://openalex.org/W3031363333","https://openalex.org/W3216401400","https://openalex.org/W6634082615"],"related_works":["https://openalex.org/W1595652908","https://openalex.org/W2089093251","https://openalex.org/W2104714048","https://openalex.org/W2950022897","https://openalex.org/W2390775476","https://openalex.org/W2186233897","https://openalex.org/W2785001934","https://openalex.org/W2408618716","https://openalex.org/W2950917560","https://openalex.org/W2114473615"],"abstract_inverted_index":{"Determination":[0],"of":[1,8,71,89],"pitch":[2,17,23,39,90,97,109,123],"in":[3],"noise":[4,116],"is":[5,46,54,63],"challenging":[6],"because":[7],"corrupted":[9],"harmonic":[10],"structure.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15],"extract":[16],"using":[18],"supervised":[19],"learning,":[20],"where":[21],"probabilistic":[22,87],"states":[24,40],"are":[25,93,112],"directly":[26],"learned":[27],"from":[28],"noisy":[29],"speech.":[30],"We":[31],"investigate":[32],"two":[33],"alternative":[34],"neural":[35,50,67],"networks":[36],"modeling":[37],"the":[38,47,64,73,107],"given":[41],"observations.":[42],"The":[43,60],"first":[44],"one":[45,62],"feedforward":[48],"deep":[49,66],"network":[51,68],"(DNN),":[52],"which":[53,92],"trained":[55,76],"on":[56,77],"static":[57],"frame-level":[58,79],"features.":[59,80],"second":[61],"recurrent":[65],"(RNN)":[69],"capable":[70],"learning":[72],"temporal":[74],"dynamics":[75],"sequential":[78],"Both":[81],"DNNs":[82],"and":[83,118],"RNNs":[84],"produce":[85],"accurate":[86],"outputs":[88],"states,":[91],"then":[94],"connected":[95],"into":[96],"contours":[98],"by":[99],"Viterbi":[100],"decoding.":[101],"Our":[102],"systematic":[103],"evaluation":[104],"shows":[105],"that":[106],"proposed":[108],"tracking":[110,124],"approaches":[111],"robust":[113],"to":[114],"different":[115],"conditions":[117],"significantly":[119],"outperform":[120],"current":[121],"state-of-the-art":[122],"techniques.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}