This paper presents a deep neural network (DNN) based spectral envelope conversion method. A global DNN is employed to model the complex non-linear mapping relationship between the spectral envelopes of source and target speakers. The proposed DNN is generatively trained layer-by-layer by cascade of two restricted Boltzmann machines (RBMs) and a bidirectional associative memory (BAM), which are...

This paper deals with the estimation of pitch from only spectral envelope information. The proposed method uses a Gaussian Mixture Model (GMM) to characterize the joint distribution of the spectral envelope parameters and pitchnormalized values. During the learning stage, the model parameters are estimated by means of the EM algorithm. Then, a regression is made which enables the determination ...

In this paper, for their use as nanoluminophors on color-conversion white light emitting diodes LEDs , we present spectrally resolved relative quantum efficiency and relative color photon conversion efficiency of CdSe/ZnS core/shell nanocrystal NC emitters in the solid-state film. We observe that both the averaged relative quantum efficiency and the averaged relative photon conversion efficienc...

Photovoltaic (PV) technologies for solar energy conversion represent promising routes to green and renewable energy generation. Despite relevant PV technologies being available for more than half a century, the production of solar energy remains costly, largely owing to low power conversion efficiencies of solar cells. The main difficulty in improving the efficiency of PV energy conversion lies...

In this paper, a voice conversion approach that combines two distinct ideas is proposed to improve the converted-voice quality. The first idea is to map spectral features, e.g. discrete cepstrum coefficients (DCC), with segmental Gaussian mixture models (GMMs). That is, a single GMM of a large number of mixture components is replaced here with several voice-content specific GMMs each consisting...