Training Personal Voice Model of a Speaker with Unified Phonetic Space of Features Using Artificial Neural Network

The paper investigates possibility of creating a personal voice model using transcribed speech samples of a specified speaker. The paper presents a practical way of building such speech model and some experimental results of applying the model to voice conversion. The model uses an artificial neural network organized as autoencoder that establishes correspondence between space of speech parameters and space of possible phonetic states, unified for any voice.