{"id":"https://openalex.org/W1484865348","doi":"https://doi.org/10.1109/icassp.2015.7178892","title":"Spectral conversion using deep neural networks trained with multi-source speakers","display_name":"Spectral conversion using deep neural networks trained with multi-source speakers","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1484865348","doi":"https://doi.org/10.1109/icassp.2015.7178892","mag":"1484865348"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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"],"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"]}]},{"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"]},{"id":"https://openalex.org/I4210133256","display_name":"Instituttet for Anvendt Datateknik (Denmark)","ror":"https://ror.org/02q83se13","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210133256"]}],"countries":["CN","DK"],"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","iFLYTEK Research, iFLYTEK Co., Ltd"],"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":"iFLYTEK Research, iFLYTEK Co., Ltd","institution_ids":["https://openalex.org/I4210133256"]}]},{"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"],"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"]}]},{"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"],"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2346,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80381454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"18","issue":null,"first_page":"4849","last_page":"4853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9979000091552734,"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/initialization","display_name":"Initialization","score":0.7695997953414917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684518098831177},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.7311155796051025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6022566556930542},{"id":"https://openalex.org/keywords/multi-source","display_name":"Multi-source","score":0.5773971676826477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.557506799697876},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.5436725616455078},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.5004315376281738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4868156611919403},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4676947593688965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35224223136901855},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.058883488178253174}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7695997953414917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684518098831177},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.7311155796051025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6022566556930542},{"id":"https://openalex.org/C2780665216","wikidata":"https://www.wikidata.org/wiki/Q6934498","display_name":"Multi-source","level":2,"score":0.5773971676826477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.557506799697876},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5436725616455078},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.5004315376281738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4868156611919403},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4676947593688965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35224223136901855},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.058883488178253174},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":18,"referenced_works":["https://openalex.org/W31448757","https://openalex.org/W1972420736","https://openalex.org/W1993882792","https://openalex.org/W2033516035","https://openalex.org/W2086796102","https://openalex.org/W2114543868","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2136922672","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2165674530","https://openalex.org/W2294351487","https://openalex.org/W2401544731","https://openalex.org/W4239943352","https://openalex.org/W6696767757","https://openalex.org/W6713064456"],"related_works":["https://openalex.org/W1829305295","https://openalex.org/W2997460609","https://openalex.org/W3000197790","https://openalex.org/W1484865348","https://openalex.org/W2109830113","https://openalex.org/W3158357639","https://openalex.org/W4292308099","https://openalex.org/W2381461328","https://openalex.org/W2066506443","https://openalex.org/W2041375496"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"method":[4,112,117],"for":[5,27,37,70,80],"voice":[6],"conversion":[7],"using":[8],"deep":[9],"neural":[10],"networks":[11],"(DNNs)":[12],"trained":[13],"with":[14,118],"multiple":[15],"source":[16,38,54,82],"speakers.":[17],"The":[18],"proposed":[19,96,111],"DNNs":[20,41,62,75,97],"can":[21,42,63,98],"be":[22,43,65],"used":[23,66],"in":[24,31],"two":[25],"ways":[26],"different":[28],"scenarios:":[29],"1)":[30],"the":[32,40,61,95,107,110,114],"absence":[33],"of":[34,73],"training":[35,78],"data":[36,79],"speaker,":[39],"treated":[44],"as":[45,67,92],"source-speaker-independent":[46,93],"models":[47,69],"and":[48,83],"perform":[49],"conversions":[50],"directly":[51],"from":[52],"arbitrary":[53],"speakers":[55,85],"to":[56,102],"certain":[57],"target":[58,84],"speaker;":[59],"2)":[60],"also":[64],"initial":[68],"further":[71],"fine-tuning":[72],"source-speaker-dependent":[74,104],"when":[76],"parallel":[77],"both":[81],"are":[86],"available.":[87],"Experimental":[88],"results":[89],"show":[90],"that,":[91],"models,":[94],"achieve":[99],"comparable":[100],"performance":[101],"conventional":[103,115],"models.":[105],"On":[106],"other":[108],"hand,":[109],"outperforms":[113],"initialization":[116],"restricted":[119],"Boltzmann":[120],"machines":[121],"(RBMs).":[122]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}