{"id":"https://openalex.org/W2699202114","doi":"https://doi.org/10.1109/icassp.2017.7953212","title":"Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion","display_name":"Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2699202114","doi":"https://doi.org/10.1109/icassp.2017.7953212","mag":"2699202114"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5091143209","display_name":"Nirmesh J. Shah","orcid":"https://orcid.org/0000-0002-7294-6757"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nirmesh J. Shah","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":1.3982,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84185367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"5520","last_page":"5524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9930999875068665,"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/spurious-relationship","display_name":"Spurious relationship","score":0.6810634136199951},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.6568979620933533},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6219035387039185},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.6085644960403442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6007063388824463},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.5646159648895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.549599289894104},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5459302067756653},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5403348207473755},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5356969237327576},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5031248927116394},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4441651999950409},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4417082965373993},{"id":"https://openalex.org/keywords/frequency-spectrum","display_name":"Frequency spectrum","score":0.44117802381515503},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4340384006500244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35211867094039917},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32047978043556213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2719634175300598},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15290796756744385},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.14847087860107422},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12339934706687927},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1231737732887268},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.10270392894744873}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6810634136199951},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.6568979620933533},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6219035387039185},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.6085644960403442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6007063388824463},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.5646159648895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.549599289894104},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5459302067756653},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5403348207473755},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5356969237327576},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5031248927116394},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4441651999950409},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4417082965373993},{"id":"https://openalex.org/C122381330","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Frequency spectrum","level":3,"score":0.44117802381515503},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4340384006500244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35211867094039917},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32047978043556213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2719634175300598},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15290796756744385},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.14847087860107422},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12339934706687927},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1231737732887268},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.10270392894744873},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4099999964237213,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W62664237","https://openalex.org/W1977362459","https://openalex.org/W2011916518","https://openalex.org/W2017425464","https://openalex.org/W2049633694","https://openalex.org/W2100649345","https://openalex.org/W2105698384","https://openalex.org/W2111550316","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2128160875","https://openalex.org/W2136166660","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2165674530","https://openalex.org/W2168810263","https://openalex.org/W2169652224","https://openalex.org/W2295406225","https://openalex.org/W2317898072","https://openalex.org/W2395273272","https://openalex.org/W2402356521","https://openalex.org/W2404839462","https://openalex.org/W2473388484","https://openalex.org/W2526493173","https://openalex.org/W2577042574","https://openalex.org/W2963879839","https://openalex.org/W6697307144","https://openalex.org/W6711789357","https://openalex.org/W6732251480"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2093562370","https://openalex.org/W2148271137"],"abstract_inverted_index":{"In":[0,40],"Frequency":[1],"Warping":[2],"(FW)-based":[3],"Voice":[4],"Conversion":[5],"(VC),":[6],"the":[7,14,17,28,32,36,52,55,59,77,96,100,122,135,147,156],"source":[8],"spectrum":[9,19,34,57,68,98,103],"is":[10,119],"modified":[11],"to":[12,26,91,109,134,146],"match":[13,93],"frequency-axis":[15],"of":[16,54,61,76,86],"target":[18,38,102],"followed":[20],"by":[21,152],"an":[22],"Amplitude":[23],"Scaling":[24],"(AS)":[25],"compensate":[27],"amplitude":[29,53],"differences":[30],"between":[31,95],"warped":[33,97],"and":[35,99,129,137,165,172],"actual":[37,101],"spectrum.":[39],"this":[41],"paper,":[42],"we":[43],"propose":[44],"a":[45,62,83],"novel":[46],"AS":[47,106,139],"technique":[48],"which":[49],"linearly":[50],"transfers":[51],"frequency-warped":[56],"using":[58],"knowledge":[60],"Gaussian":[63],"Mixture":[64],"Model":[65],"(GMM)-based":[66],"converted":[67,112],"without":[69],"adding":[70],"any":[71],"spurious":[72],"peaks.":[73],"The":[74],"novelty":[75],"proposed":[78,123],"approach":[79],"lies":[80],"in":[81,104,111,155],"avoiding":[82],"perceptual":[84],"impression":[85],"wrong":[87],"formant":[88],"location":[89],"(due":[90],"perfect":[92],"assumption":[94],"state-of-the-art":[105,138,173],"method)":[107],"leading":[108],"deterioration":[110],"voice":[113,142],"quality.":[114],"From":[115],"subjective":[116],"analysis,":[117],"it":[118],"evident":[120],"that":[121],"system":[124],"has":[125],"been":[126],"preferred":[127,169],"33.81%":[128],"12.37%":[130],"times":[131,163,167],"more":[132,164],"compared":[133],"GMM":[136,171],"method":[140],"for":[141],"quality,":[143],"respectively.":[144,176],"Similar":[145],"quality":[148],"conversion":[149,160],"trade-offs":[150],"observed":[151],"other":[153],"studies":[154],"literature,":[157],"speaker":[158],"identity":[159],"was":[161],"0.73%":[162],"9.09%":[166],"less":[168],"over":[170],"AS-based":[174],"method,":[175]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}