Skip to main navigation Skip to search Skip to main content

Using Gaussian processes to synthesise voiced speech with natural pitch variations

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This short paper demonstrates an application of Gaussian-Processes to voiced speech synthesis. The novelty lies in the application of an auxiliary input, which acts to vary the pitch of the synthesised sound. The ability to alter pitch has often been a difficulty of nonlinear speech syntheisers.

Original languageEnglish
Title of host publication14th International Conference on Digital Signal Processing, 2002
EditorsA N Skodras, A G Constantinides
PublisherIEEE
Pages321-324
Number of pages4
Volume1
ISBN (Print)0-7803-7503-3
DOIs
Publication statusPublished - 2002
Event14th International Conference on Digital Signal Processing - Santorini
Duration: 1 Jul 2002 → 3 Jul 2002

Conference

Conference14th International Conference on Digital Signal Processing
Abbreviated titleDSP 2002
CitySantorini
Period1/07/02 → 3/07/02

Fingerprint

Dive into the research topics of 'Using Gaussian processes to synthesise voiced speech with natural pitch variations'. Together they form a unique fingerprint.

Cite this