Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS system

TL;DR

This paper evaluates the controllability of an expressive deep learning-based TTS system using both objective acoustic feature correlation measures and subjective user perception experiments.

Contribution

It provides a comprehensive assessment of controllability in expressive TTS, combining objective metrics and subjective user studies to evaluate system performance.

Findings

Correlation between acoustic features and latent space dimensions

User ability to retrieve matching expressiveness in perceptual tests

Insights into controllability effectiveness of the TTS system

Abstract

In this paper, we study the controllability of an Expressive TTS system trained on a dataset for a continuous control. The dataset is the Blizzard 2013 dataset based on audiobooks read by a female speaker containing a great variability in styles and expressiveness. Controllability is evaluated with both an objective and a subjective experiment. The objective assessment is based on a measure of correlation between acoustic features and the dimensions of the latent space representing expressiveness. The subjective assessment is based on a perceptual experiment in which users are shown an interface for Controllable Expressive TTS and asked to retrieve a synthetic utterance whose expressiveness subjectively corresponds to that a reference utterance.