Voice conversion (VC) using sequence-to-sequence learning of context posterior probabilities is proposed. Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior probabilities estimated from the source speech parameters. Although conventional VC can be built from non-parallel data, it is difficult to convert speaker individuality such as phonetic property and speaking rate contained in the posterior probabilities because the source posterior probabilities are directly used for predicting target speech parameters. In this work, we assume that the training data partly include parallel speech data and propose sequence-to-sequence learning between the source and target posterior probabilities. The conversion models perform non-linear and variable-length transformation from the source probability sequence to the target one. Further, we propose a joint training algorithm for the modules. In contrast to conventional VC, which separately trains the speech recognition that estimates posterior probabilities and the speech synthesis that predicts target speech parameters, our proposed method jointly trains these modules along with the proposed probability conversion modules. Experimental results demonstrate that our approach outperforms the conventional VC.
Scallop shell powder heated at 1,000 degrees C for 1 h exhibited sporicidal action against Bacillus subtilis spores. The sporicidal kinetics of this action were analyzed with the use of a nonlogarithmic model. Apparent death rate constants (k) were obtained under various conditions. The value of k increased with powder concentration but became constant beyond the concentration representing the solubility of Ca(OH)2. A linear inverse relationship between k and temperature was found, and from this relationship the activation energy required for the death of B. subtilis spores in the heated shell powder slurry could be determined.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.