TOP > 外国特許検索 > VOICE QUALITY CONVERSION DEVICE, VOICE QUALITY CONVERSION METHOD AND PROGRAM

VOICE QUALITY CONVERSION DEVICE, VOICE QUALITY CONVERSION METHOD AND PROGRAM NEW

外国特許コード F180009512
整理番号 (S2017-0325-N0)
掲載日 2018年11月2日
出願国 世界知的所有権機関(WIPO)
国際出願番号 2018JP007268
国際公開番号 WO 2018159612
国際出願日 平成30年2月27日(2018.2.27)
国際公開日 平成30年9月7日(2018.9.7)
優先権データ
  • 特願2017-036109 (2017.2.28) JP
発明の名称 (英語) VOICE QUALITY CONVERSION DEVICE, VOICE QUALITY CONVERSION METHOD AND PROGRAM NEW
発明の概要(英語) This voice quality conversion device is provided with a parameter learning unit, a parameter storage unit and a voice quality conversion processing unit. The parameter learning unit prepares a probability model by means of a restricted Boltzmann machine assuming that there is a connection weight between a visible element representing input data and a hidden element representing potential information. The parameter learning unit defines, as the probability model, a plurality of speaker clusters having unique adaptive matrices, and determines parameters for each speaker by estimating weights for the plurality of speaker clusters. The parameter storage unit stores the parameters. The voice quality conversion processing unit performs voice quality conversion processing of voice information based on the voice of an input speaker on the basis of the parameters stored by the parameter storage unit and speaker information of a target speaker.
従来技術、競合技術の概要(英語) BACKGROUND ART
Conventional, the input of the speaker's voice while maintaining phonetic information, only information relating to the speaker of the speaker output to convert the field of voice conversion technology, at the time of learning of the model, the input speech by the speaker and the output of the speaker in the same parallel data to the speech-to-voice conversion is mainly used in parallel., GMM(Gaussian Mixture Model), NMF(Non-negative Matrix Factrization) as the voice conversion method based on the parallel-based method such as a method based on, DNN(Deep Neural Network), various statistical approach has been proposed (see Patent Document 1).Voice conversion in parallel, by virtue of the parallel constraint and a relatively high accuracy is obtained on the other hand, as the learning data in the output speech of the speaker input and the speaker is required that the contents agree with each other, a problem that the convenience is impaired.
On the other hand, upon learning of the model described above does not use the parallel data of a non-parallel to the voice conversion is getting much attention.Voice conversion is non-parallel, parallel-to-voice conversion as compared to speech degrades the precision of the freedom can be performed by learning using the convenience and practicability is high.Is the non-patent document 1, the input voice of a speaker output the voice of the individual parameters in advance using the learning in advance, the learning data included in the speaker or target speaker and input speaker voice conversion technique can be described.
  • 出願人(英語)
  • ※2012年7月以前掲載分については米国以外のすべての指定国
  • THE UNIVERSITY OF ELECTRO-COMMUNICATIONS
  • 発明者(英語)
  • Midorikawa
国際特許分類(IPC)
指定国 National States: AE AG AL AM AO AT AU AZ BA BB BG BH BN BR BW BY BZ CA CH CL CN CO CR CU CZ DE DJ DK DM DO DZ EC EE EG ES FI GB GD GE GH GM GT HN HR HU ID IL IN IR IS JO JP KE KG KH KN KP KR KW KZ LA LC LK LR LS LU LY MA MD ME MG MK MN MW MX MY MZ NA NG NI NO NZ OM PA PE PG PH PL PT QA RO RS RU RW SA SC SD SE SG SK SL SM ST SV SY TH TJ TM TN TR TT TZ UA UG US UZ VC VN ZA ZM ZW
ARIPO: BW GH GM KE LR LS MW MZ NA RW SD SL SZ TZ UG ZM ZW
EAPO: AM AZ BY KG KZ RU TJ TM
EPO: AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
OAPI: BF BJ CF CG CI CM GA GN GQ GW KM ML MR NE SN ST TD TG
ライセンスをご希望の方、特許の内容に興味を持たれた方は、下記までご連絡ください

PAGE TOP

close
close
close
close
close
close