Dmytro Bielievtsov


CTO at Respeecher

Dmytro've been working on the problem of voice conversion for the last two years or something, applies deep learning to do speech processing for a spectrum of b2b markets. Our prototype first product allows you to speak with the voice of someone else (e.g., a famous person -- all that is needed to train the system is samples of your voice and the target voice). In the past, he worked as Research assistant, Software Engineer at Berlin Institute of Technology and Institute for Theoretical Biology at HU Berlin

Topic of presentation: Variational autoencoders for speech processing

The main points of the presentation: Variational autoencoders (or VAE) have become one of the most popular unsupervised learning techniques for modelling complex data distributions, such as images and audio. In this talk I'll begin with a general introduction to VAEs and then review a recent technique called VQ-VAE which is capable of learning rundimentary phoneme-level language model from raw audio without any supervision.