{"id":"https://openalex.org/W2913006054","doi":"https://doi.org/10.1109/icdsp.2018.8631888","title":"Whisper to Normal Speech Based on Deep Neural Networks with MCC and F0 Features","display_name":"Whisper to Normal Speech Based on Deep Neural Networks with MCC and F0 Features","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913006054","doi":"https://doi.org/10.1109/icdsp.2018.8631888","mag":"2913006054"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2018.8631888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","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/A5103280008","display_name":"Hailun Lian","orcid":"https://orcid.org/0000-0002-0519-8568"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailun Lian","raw_affiliation_strings":["MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102016818","display_name":"Yuting Hu","orcid":"https://orcid.org/0000-0002-5677-9952"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Hu","raw_affiliation_strings":["MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067137933","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-6509-5520"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066775159","display_name":"Huabin Wang","orcid":"https://orcid.org/0000-0001-5938-5409"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huabin Wang","raw_affiliation_strings":["MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101709936","display_name":"Liang Tao","orcid":"https://orcid.org/0000-0001-8553-8421"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Tao","raw_affiliation_strings":["MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.1662,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.5,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773533821105957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7452871799468994},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.650130033493042},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.612430989742279},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6073914170265198},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6008707880973816},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5802094340324402},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5250415802001953},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4111926257610321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.394858181476593},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.381069540977478},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2589539587497711},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18948885798454285},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07989665865898132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773533821105957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7452871799468994},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.650130033493042},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.612430989742279},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6073914170265198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6008707880973816},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5802094340324402},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5250415802001953},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4111926257610321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.394858181476593},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.381069540977478},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2589539587497711},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18948885798454285},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07989665865898132},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2018.8631888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W162035042","https://openalex.org/W1540787848","https://openalex.org/W1665214252","https://openalex.org/W1926768285","https://openalex.org/W2037288988","https://openalex.org/W2047233879","https://openalex.org/W2062417847","https://openalex.org/W2066502876","https://openalex.org/W2086796102","https://openalex.org/W2119648481","https://openalex.org/W2120605154","https://openalex.org/W2147800946","https://openalex.org/W2162223813","https://openalex.org/W2511640485","https://openalex.org/W2740504963","https://openalex.org/W2775672830","https://openalex.org/W2963285578","https://openalex.org/W6637242042","https://openalex.org/W6681775333","https://openalex.org/W6685562342"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2387604097","https://openalex.org/W1980297060","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1986772939","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W1996938627"],"abstract_inverted_index":{"In":[0,89],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"method":[6],"of":[7,62,87,92,103,112,143],"converting":[8],"whisper":[9,27],"to":[10,28,51,59,124],"normal":[11,29,71,104],"speech,":[12],"using":[13,99],"low":[14,63],"dimensional":[15,64],"Mel":[16],"Cepstral":[17],"Coefficients":[18],"(MCC)":[19],"combined":[20],"with":[21],"Deep":[22],"Neural":[23],"Networks":[24],"(DNN).":[25],"The":[26,46],"speech":[30,68,105,117,135,144],"conversion":[31,40],"is":[32,97],"divided":[33],"into":[34],"two":[35],"modules,":[36],"that":[37,132],"is,":[38],"spectrum":[39,54],"and":[41,69,106,115,146],"fundamental":[42,110],"frequency":[43,111],"(F0)":[44],"estimation.":[45],"MCC":[47,65,100],"features":[48,101],"are":[49,119],"used":[50],"characterize":[52],"the":[53,78,85,90,95,109,113,126,133,141],"envelope.":[55],"We":[56],"use":[57],"DNN":[58,73],"model":[60],"relationship":[61],"between":[66],"whispered":[67],"its":[70],"counterpart.":[72],"can":[74,82],"not":[75],"only":[76],"fit":[77],"data":[79],"well,":[80],"but":[81],"also":[83],"tackle":[84],"issue":[86],"smoothness.":[88],"module":[91],"F0":[93,96],"estimation,":[94],"estimated":[98,120],"both":[102,139],"whisper.":[107],"Specifically,":[108],"voice":[114],"unvoiced":[116],"frame":[118],"simultaneously":[121],"in":[122,140],"order":[123],"reduce":[125],"modeling":[127],"complexity.":[128],"Experimental":[129],"results":[130],"show":[131],"converted":[134],"gains":[136],"better":[137],"performance":[138],"aspect":[142],"quality":[145],"intelligibility.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}