{"id":"https://openalex.org/W2010833326","doi":"https://doi.org/10.1109/icassp.2014.6855135","title":"Using bidirectional associative memories for joint spectral envelope modeling in voice conversion","display_name":"Using bidirectional associative memories for joint spectral envelope modeling in voice conversion","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2010833326","doi":"https://doi.org/10.1109/icassp.2014.6855135","mag":"2010833326"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5100343775","display_name":"Lijuan Liu","orcid":"https://orcid.org/0000-0001-6804-848X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Juan Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling-Hui Chen","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.4474,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83905031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"7884","last_page":"7888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/T10320","display_name":"Neural Networks and Applications","score":0.9970999956130981,"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/spectral-envelope","display_name":"Spectral envelope","score":0.680054783821106},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.6371957063674927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6258155703544617},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5558034777641296},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5442997217178345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5172206163406372},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.508660614490509},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48881956934928894},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4641472101211548},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.45618736743927},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4376411437988281},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43432140350341797},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4291653633117676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42769479751586914},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.4255220293998718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35619252920150757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35497182607650757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3265698254108429},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2856721878051758},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1271952986717224},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1013936996459961},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09867295622825623},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08675798773765564}],"concepts":[{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.680054783821106},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.6371957063674927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258155703544617},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5558034777641296},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5442997217178345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5172206163406372},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.508660614490509},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48881956934928894},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4641472101211548},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45618736743927},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4376411437988281},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43432140350341797},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4291653633117676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42769479751586914},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.4255220293998718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35619252920150757},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35497182607650757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3265698254108429},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2856721878051758},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1271952986717224},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1013936996459961},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09867295622825623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08675798773765564},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6855135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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":15,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W44815768","https://openalex.org/W2020024436","https://openalex.org/W2049686551","https://openalex.org/W2095425517","https://openalex.org/W2116064496","https://openalex.org/W2116257577","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2136166660","https://openalex.org/W2164700406","https://openalex.org/W2203070340","https://openalex.org/W2401544731","https://openalex.org/W6601785968","https://openalex.org/W6713064456"],"related_works":["https://openalex.org/W2916681395","https://openalex.org/W2529583158","https://openalex.org/W1575733688","https://openalex.org/W2963348254","https://openalex.org/W1641020902","https://openalex.org/W3128475979","https://openalex.org/W2133316674","https://openalex.org/W1968450737","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"The":[0,78,89],"spectral":[1,23,75],"envelope":[2,24,76],"is":[3,16,27,42,120],"the":[4,21,52,74,85,106,114,117,125],"most":[5],"natural":[6],"representation":[7],"of":[8,80,116],"speech":[9],"signal.":[10],"But":[11],"in":[12,55,70],"voice":[13,110],"conversion,":[14],"it":[15],"difficult":[17],"to":[18,64,72],"directly":[19],"model":[20,51,73],"raw":[22],"space,":[25],"which":[26],"high":[28,56],"dimensional":[29,57],"and":[30],"strongly":[31],"cross-dimensional":[32,53],"correlated,":[33],"with":[34,102,124],"conventional":[35,126],"Gaussian":[36,68],"distributions.":[37],"Bidirectional":[38],"associative":[39],"memory":[40],"(BAM)":[41],"a":[43],"two-layer":[44],"feedback":[45],"neural":[46],"network":[47],"that":[48,94,113],"can":[49],"better":[50,97],"correlations":[54],"vectors.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"reformulate":[65],"BAMs":[66,81,95],"as":[67],"distributions":[69],"order":[71],"space.":[77],"parameters":[79],"are":[82],"estimated":[83],"using":[84],"contrastive":[86],"divergence":[87],"algorithm.":[88],"evaluations":[90],"on":[91,109],"likelihood":[92],"show":[93],"have":[96],"modeling":[98],"ability":[99],"than":[100],"Gaussians":[101],"diagonal":[103],"covariance.":[104],"And":[105],"subjective":[107],"tests":[108],"conversion":[111],"indicate":[112],"performance":[115],"proposed":[118],"method":[119],"significantly":[121],"improved":[122],"comparing":[123],"GMM":[127],"based":[128],"method.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}