{"id":"https://openalex.org/W2400225965","doi":"https://doi.org/10.1109/icassp.2016.7472680","title":"Robust pitch tracking in noisy speech using speaker-dependent deep neural networks","display_name":"Robust pitch tracking in noisy speech using speaker-dependent deep neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400225965","doi":"https://doi.org/10.1109/icassp.2016.7472680","mag":"2400225965"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101800003","display_name":"Yuzhou Liu","orcid":"https://orcid.org/0000-0002-7030-9121"},"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":true,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101800003"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70388234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"495","issue":null,"first_page":"5255","last_page":"5259"},"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":0.9998999834060669,"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":0.9995999932289124,"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/speech-recognition","display_name":"Speech recognition","score":0.7929650545120239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648420333862305},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5462354421615601},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5398837924003601},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.49452802538871765},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4417106509208679},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4371914863586426},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4341007173061371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4018024206161499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37187880277633667},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36363762617111206},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09106612205505371}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7929650545120239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648420333862305},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5462354421615601},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5398837924003601},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.49452802538871765},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4417106509208679},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4371914863586426},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4341007173061371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018024206161499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37187880277633667},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36363762617111206},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09106612205505371}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W50577135","https://openalex.org/W1875231349","https://openalex.org/W1904365287","https://openalex.org/W1974387177","https://openalex.org/W1989549063","https://openalex.org/W1990449877","https://openalex.org/W1993064527","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2034300186","https://openalex.org/W2045956438","https://openalex.org/W2055611715","https://openalex.org/W2061140267","https://openalex.org/W2079623482","https://openalex.org/W2091425152","https://openalex.org/W2115129089","https://openalex.org/W2135431242","https://openalex.org/W2142384583","https://openalex.org/W2143341575","https://openalex.org/W2156387975","https://openalex.org/W2408151586","https://openalex.org/W4231807801","https://openalex.org/W4233392025","https://openalex.org/W6639350448","https://openalex.org/W6640036494","https://openalex.org/W6682889407","https://openalex.org/W6713937784"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"A":[0],"reliable":[1],"estimate":[2,43],"of":[3,32,75,100],"pitch":[4,45,91,112],"in":[5,115],"noisy":[6],"speech":[7,12],"is":[8,61,67,72,86],"crucial":[9],"for":[10,55],"many":[11],"applications.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"propose":[18],"to":[19,27,89],"use":[20],"speaker-dependent":[21,65],"(SD)":[22],"deep":[23],"neural":[24],"networks":[25],"(DNNs)":[26],"model":[28],"the":[29],"harmonic":[30],"patterns":[31],"each":[33,48],"speaker.":[34],"Specifically,":[35],"SD-DNNs":[36,101],"take":[37],"spectral":[38],"features":[39],"as":[40,107,109],"input":[41],"and":[42],"probabilistic":[44],"states":[46],"at":[47],"time":[49],"frame.":[50],"We":[51],"investigate":[52],"two":[53],"methods":[54,99],"SD-DNN":[56],"training.":[57],"The":[58,69,83],"first":[59],"one":[60,71],"direct":[62],"training":[63,98],"when":[64],"data":[66],"sufficient.":[68],"second":[70],"speaker":[73],"adaptation":[74],"a":[76,110],"speaker-independent":[77],"(SI)":[78],"DNN":[79],"with":[80],"limited":[81],"data.":[82],"Viterbi":[84],"algorithm":[85,114],"then":[87],"used":[88],"track":[90],"through":[92],"time.":[93],"Experiments":[94],"show":[95],"that":[96],"both":[97],"outperform":[102],"an":[103],"SI-DNN":[104],"based":[105],"system":[106],"well":[108],"state-of-the-art":[111],"tracking":[113],"all":[116],"SNR":[117],"conditions.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}