Back to Results
First PageMeta Content
Cybernetics / Computational linguistics / Artificial intelligence / Machine learning / Computational statistics / Artificial neural network / Speech recognition / Backpropagation / Supervised learning / Neural networks / Computational neuroscience / Science


INTERSPEECHSequence Error (SE) Minimization Training of Neural Network for Voice Conversion Feng-Long Xie1,2∗ , Yao Qian2 , Yuchen Fan2 , Frank K. Soong2 , Haifeng Li1 1
Add to Reading List

Document Date: 2014-10-20 08:23:22

Open Document

File Size: 935,08 KB

Share Result on Facebook

City

Beijing / /

Company

ContextDependent Deep Neural Networks / Amazon / Spectral Mapping Using Artifical Neural Networks / Deep Neural Networks / /

Country

China / Singapore / /

/

Facility

Harbin Institute of Technology / Carnegie Mellon University / Language Technologies Institute / /

IndustryTerm

generation algorithm / neural network / mini-batch based stochastic gradient descent algorithm / parameter generation algorithm / approximate contrastive divergence algorithm / deeper network / /

Organization

FE SE / Harbin Institute of Technology / Harbin / Carnegie Mellon University / BDL DBN / Indian KSP / /

Person

W. Hu / Utterances Feature / V. Vanhoucke / /

/

Position

source speaker / target speaker / speaker / source/target speaker / source and target speaker / /

Product

Altec XT1 Speakers / /

ProgrammingLanguage

LPC / /

Technology

Speech Recognition / mini-batch based stochastic gradient descent algorithm / Neural Network / generation algorithm / Mini-batch algorithms / parameter generation algorithm / simulation / Image Processing / approximate contrastive divergence algorithm / /

URL

http /

SocialTag