{"id":"https://openalex.org/W2981664394","doi":"https://doi.org/10.1109/jstsp.2019.2949422","title":"Prediction of Creaky Speech by Recurrent Neural Networks Using Psychoacoustic Roughness","display_name":"Prediction of Creaky Speech by Recurrent Neural Networks Using Psychoacoustic Roughness","publication_year":2019,"publication_date":"2019-10-24","ids":{"openalex":"https://openalex.org/W2981664394","doi":"https://doi.org/10.1109/jstsp.2019.2949422","mag":"2981664394"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2949422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2949422","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal 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/A5089738382","display_name":"Juli\u00e1n Villegas","orcid":"https://orcid.org/0000-0003-1891-1753"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Julian Villegas","raw_affiliation_strings":["Computer Arts Laboratory, University of Aizu, Aizu-Wakamatsu, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1891-1753","affiliations":[{"raw_affiliation_string":"Computer Arts Laboratory, University of Aizu, Aizu-Wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Aizu-Wakamatsu, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1838-4789","affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Aizu-Wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048204253","display_name":"Jeremy Perkins","orcid":"https://orcid.org/0000-0002-7800-4234"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jeremy Perkins","raw_affiliation_strings":["Centre for Language Research, University of Aizu, Aizu-Wakamatsu, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7800-4234","affiliations":[{"raw_affiliation_string":"Centre for Language Research, University of Aizu, Aizu-Wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070387555","display_name":"Seunghun J. Lee","orcid":"https://orcid.org/0000-0001-5634-5583"},"institutions":[{"id":"https://openalex.org/I199080787","display_name":"International Christian University","ror":"https://ror.org/01cg0k189","country_code":"JP","type":"education","lineage":["https://openalex.org/I199080787"]},{"id":"https://openalex.org/I84929415","display_name":"University of Venda","ror":"https://ror.org/0338xea48","country_code":"ZA","type":"education","lineage":["https://openalex.org/I84929415"]}],"countries":["JP","ZA"],"is_corresponding":false,"raw_author_name":"Seunghun J. Lee","raw_affiliation_strings":["International Christian University, Tokyo, Japan","University of Venda, Thohoyandou, South Africa"],"raw_orcid":"https://orcid.org/0000-0001-5634-5583","affiliations":[{"raw_affiliation_string":"International Christian University, Tokyo, Japan","institution_ids":["https://openalex.org/I199080787"]},{"raw_affiliation_string":"University of Venda, Thohoyandou, South Africa","institution_ids":["https://openalex.org/I84929415"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8345,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73930245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"14","issue":"2","first_page":"355","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.7603901624679565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556382417678833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6263065338134766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5856800079345703},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4865971803665161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722713232040405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4487716257572174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32129570841789246},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.06794473528862}],"concepts":[{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.7603901624679565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556382417678833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6263065338134766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5856800079345703},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4865971803665161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722713232040405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4487716257572174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32129570841789246},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.06794473528862},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2019.2949422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2949422","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W101251843","https://openalex.org/W134885506","https://openalex.org/W144053593","https://openalex.org/W1483501585","https://openalex.org/W1545798667","https://openalex.org/W1588718109","https://openalex.org/W1893685658","https://openalex.org/W1966948181","https://openalex.org/W1971243715","https://openalex.org/W1982116442","https://openalex.org/W1986647000","https://openalex.org/W1998446020","https://openalex.org/W2001257796","https://openalex.org/W2008806652","https://openalex.org/W2010070470","https://openalex.org/W2011585205","https://openalex.org/W2014268732","https://openalex.org/W2018845141","https://openalex.org/W2022194925","https://openalex.org/W2022939667","https://openalex.org/W2027306502","https://openalex.org/W2043843997","https://openalex.org/W2048488652","https://openalex.org/W2048939276","https://openalex.org/W2051457717","https://openalex.org/W2063252428","https://openalex.org/W2069929513","https://openalex.org/W2083660934","https://openalex.org/W2085464700","https://openalex.org/W2085662862","https://openalex.org/W2087445608","https://openalex.org/W2095176743","https://openalex.org/W2096760972","https://openalex.org/W2101200748","https://openalex.org/W2106182759","https://openalex.org/W2122334831","https://openalex.org/W2136101712","https://openalex.org/W2137509658","https://openalex.org/W2145677425","https://openalex.org/W2146791824","https://openalex.org/W2151251521","https://openalex.org/W2152002570","https://openalex.org/W2153903782","https://openalex.org/W2187453091","https://openalex.org/W2234562586","https://openalex.org/W2276507533","https://openalex.org/W2282871646","https://openalex.org/W2406815669","https://openalex.org/W2484433477","https://openalex.org/W2574055028","https://openalex.org/W2582743722","https://openalex.org/W2615879453","https://openalex.org/W2626490650","https://openalex.org/W2742149109","https://openalex.org/W2770890514","https://openalex.org/W2796384094","https://openalex.org/W2810015715","https://openalex.org/W2946306303","https://openalex.org/W2980185458","https://openalex.org/W3134665153","https://openalex.org/W3150150402","https://openalex.org/W3216401400","https://openalex.org/W4230096730","https://openalex.org/W4298366219","https://openalex.org/W4399547459","https://openalex.org/W6605851058","https://openalex.org/W6635242286","https://openalex.org/W6675835573","https://openalex.org/W6714063201","https://openalex.org/W6732028006","https://openalex.org/W6739343589","https://openalex.org/W6741822272","https://openalex.org/W6769242506","https://openalex.org/W6791381635","https://openalex.org/W7067445421"],"related_works":["https://openalex.org/W2016620782","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2047214610","https://openalex.org/W2578422401"],"abstract_inverted_index":{"The":[0,122],"use":[1],"of":[2,10,22,29,48,90,99,112,130,146],"a":[3,8,34],"psychoacoustic":[4],"roughness":[5,19,55,91,137],"model":[6],"as":[7],"predictor":[9,125],"creaky":[11,147],"voice":[12],"is":[13],"reported.":[14],"We":[15],"found":[16],"that":[17,62,136],"the":[18,27,46,77,88,97,100,107,113,119],"temporal":[20],"profile":[21],"vocalic":[23,51],"segments":[24,52],"can":[25],"predict":[26,45],"presence":[28,47],"creakiness":[30,49,131],"in":[31,50,149],"speech.":[32,150],"Using":[33],"simple":[35],"bi-directional":[36],"Recurrent":[37],"Neural":[38],"Network":[39],"(rnn),":[40],"we":[41],"were":[42],"able":[43],"to":[44,61],"from":[53],"only":[54],"traces":[56],"with":[57,64,87],"an":[58],"accuracy":[59],"similar":[60],"obtained":[63],"rnns":[65,86],"trained":[66],"on":[67],"at":[68],"least":[69],"12-dimensional":[70],"input":[71,94,114],"data":[72,95],"(including":[73],"amplitude":[74],"difference":[75],"between":[76],"first":[78],"two":[79],"harmonics,":[80],"residual":[81],"peak":[82],"prominence,":[83],"etc.).":[84],"Training":[85],"combination":[89],"and":[92,128,134],"multidimensional":[93],"improved":[96],"performance":[98],"predictor,":[101],"but":[102],"not":[103,117],"significantly.":[104],"Likewise,":[105],"augmenting":[106],"dataset":[108],"by":[109],"time":[110],"derivatives":[111],"features":[115],"did":[116],"improve":[118],"predictor's":[120],"performance.":[121],"proposed":[123],"roughness-based":[124],"eases":[126],"interpretation":[127],"comparison":[129],"among":[132],"corpora":[133],"suggests":[135],"prediction":[138],"models":[139],"could":[140],"be":[141],"successfully":[142],"used":[143],"for":[144],"classification":[145],"intervals":[148]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}