Eigenresiduals for improved Parametric Speech Synthesis

TL;DR

This paper introduces a PCA-based eigenresidual excitation model for parametric speech synthesis that reduces buzziness and improves sound quality while maintaining a small synthesis engine footprint.

Contribution

It proposes a novel PCA-based excitation model for speech synthesis that enhances naturalness and reduces buzziness compared to traditional methods.

Findings

Improved speech quality with eigenresiduals over traditional excitation.

Maintained small synthesis engine footprint (~1MB).

Effective reduction of buzziness in synthesized speech.

Abstract

Statistical parametric speech synthesizers have recently shown their ability to produce natural-sounding and flexible voices. Unfortunately the delivered quality suffers from a typical buzziness due to the fact that speech is vocoded. This paper proposes a new excitation model in order to reduce this undesirable effect. This model is based on the decomposition of pitch-synchronous residual frames on an orthonormal basis obtained by Principal Component Analysis. This basis contains a limited number of eigenresiduals and is computed on a relatively small speech database. A stream of PCA-based coefficients is added to our HMM-based synthesizer and allows to generate the voiced excitation during the synthesis. An improvement compared to the traditional excitation is reported while the synthesis engine footprint remains under about 1Mb.