Creating Digital Voices

Abstract

My research this year primarily focuses on the creation of digital voices for use in a Text-To-Speech (TTS) system. The system which I have chosen to primarily work with is the Festival Speech Synthesis System . This package is developed by The Centre for Speech Technology Research at Edinburgh University, it is an Open Source TTS system that has capabilities to support multiple languages and voices.

The main focus of the work is looking at the creation of a number of voices in Festival with the final aim of creating a tool that can help automate a lot the processes involved in the creation of a voice.

The work is still in the early stages and more information will be made available as the year goes on.

Participants

Technical Reports

[1] Matthew Hood. Creating voices for festival text to speech system. Technical report, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, October 2004. [PDF] [BibTeX]

[2] Matthew Hood. Creating voices for festival speech synthesis system. Technical Report Literature Review, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, June 2004. [PDF] [BibTeX]

[3] Matthew Hood. Creating voices for a diphone based text to speech system. Technical Report Poster, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, August 2004. [PDF] [BibTeX]

[4] Matthew Hood. Creating a voice for festival speech synthesis system. Technical Report Honours Project Report, Virtual Reality Special Interest Group, Computer Science Department, Rhodes University, Grahamstown, South Africa, November 2004. [PDF] [BibTeX]

Images