Alexander Sorin — accepted AI-conference papers

2017

Voice-transformation-based data augmentation for prosodic classification

Raul Fernandez, Andrew Rosenberg, Alexander Sorin, Bhuvana Ramabhadran, Ron Hoory

ICASSP 2017accepted

In this work we explore data-augmentation techniques for the task of improving the performance of a supervised recurrent-neural-network classifier tasked with predicting prosodic-boundary and pitch-accent labels. The technique is based on applying voice transformations to the training data that modi…

Cited by 12 Source ↗Scholar ↗

2015

Coherent modification of pitch and energy for expressive prosody implantation

Alexander Sorin, Slava Shechtman, Vincent Pollet

ICASSP 2015accepted

In expressive TTS and voice transformation systems, implantation of expressive prosody derived from external out-of-domain sources often leads to extreme pitch modification that compromises the naturalness of the synthesized speech. In this work we investigate and prove a hypothesis that the natural…

Cited by 0 Source ↗Scholar ↗