{"id":"https://openalex.org/W2406544397","doi":"https://doi.org/10.1109/icassp.2016.7471741","title":"Convolutional neural network for robust pitch determination","display_name":"Convolutional neural network for robust pitch determination","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406544397","doi":"https://doi.org/10.1109/icassp.2016.7471741","mag":"2406544397"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471741","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/A5108811679","display_name":"Hong Su","orcid":"https://orcid.org/0009-0001-7780-9268"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Su","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108035744","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0003-0601-3905"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5526,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.90196423,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"579","last_page":"583"},"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":0.9998000264167786,"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":0.9909999966621399,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7572208046913147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526117563247681},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.7229833602905273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5894378423690796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49381908774375916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4783156216144562},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4613592326641083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44016608595848083},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42625582218170166},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3651040196418762},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21861708164215088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13580355048179626}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7572208046913147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526117563247681},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.7229833602905273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5894378423690796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49381908774375916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4783156216144562},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4613592326641083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44016608595848083},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42625582218170166},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3651040196418762},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21861708164215088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13580355048179626},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471741","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1554094125","https://openalex.org/W1875231349","https://openalex.org/W1990449877","https://openalex.org/W1993064527","https://openalex.org/W2004163116","https://openalex.org/W2008415856","https://openalex.org/W2013712815","https://openalex.org/W2034300186","https://openalex.org/W2052252043","https://openalex.org/W2055911634","https://openalex.org/W2061140267","https://openalex.org/W2085191029","https://openalex.org/W2091425152","https://openalex.org/W2100989275","https://openalex.org/W2115098197","https://openalex.org/W2115129089","https://openalex.org/W2119599673","https://openalex.org/W2123038074","https://openalex.org/W2135431242","https://openalex.org/W2138039466","https://openalex.org/W2141125852","https://openalex.org/W2160815625","https://openalex.org/W2172485033","https://openalex.org/W2570759978","https://openalex.org/W3141523618"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2149528081","https://openalex.org/W2955597484","https://openalex.org/W1990055248","https://openalex.org/W3110551121","https://openalex.org/W2349264490","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743"],"abstract_inverted_index":{"Pitch":[0],"is":[1,8,19,89],"an":[2],"important":[3],"characteristic":[4],"of":[5,86],"speech":[6],"and":[7,48,67,76],"useful":[9],"for":[10,44,51,91,97],"many":[11],"applications.":[12],"However,":[13],"pitch":[14,32,45,52,65,98],"determination":[15],"in":[16],"noisy":[17,77],"conditions":[18],"difficult.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,40],"propose":[25],"a":[26,34,42],"supervised":[27],"learning":[28],"algorithm":[29],"to":[30,73,83],"estimate":[31],"using":[33],"convolutional":[35],"neural":[36],"network":[37],"(CNN).":[38],"Specifically,":[39],"use":[41,85],"CNN":[43],"candidate":[46],"selection,":[47],"dynamic":[49],"programming":[50],"tracking.":[53],"Our":[54],"experimental":[55],"results":[56],"show":[57,69],"that":[58],"the":[59,81,84,93],"proposed":[60],"method":[61],"can":[62],"obtain":[63],"accurate":[64],"estimation":[66],"they":[68],"good":[70],"generalization":[71],"ability":[72],"new":[74],"speakers":[75],"conditions.":[78],"We":[79],"credit":[80],"success":[82],"CNN,":[87],"which":[88],"suitable":[90],"modeling":[92],"shift-invariant":[94],"spectral":[95],"feature":[96],"detection.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
