Preez, “Statistical speech synthesis for the blizzard challenge 2008

In this paper we present the details of our first entry for the Blizzard Challenge 2008 speech synthesis evaluation. Our system is a new HMM-based text-to-speech voice building system for the HTS runtime synthesis engine. We entered two UK English voices, one built from the full database provided, A...

Full description

Bibliographic Details
Main Authors: Pieter Scholtz, Albert Visagie, Johan Du Preez
Other Authors: The Pennsylvania State University CiteSeerX Archives
Format: Text
Language:English
Published: 2008
Subjects:
Online Access:http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.9284
http://www.festvox.org/blizzard/bc2008/suclast_Blizzard2008.pdf
Description
Summary:In this paper we present the details of our first entry for the Blizzard Challenge 2008 speech synthesis evaluation. Our system is a new HMM-based text-to-speech voice building system for the HTS runtime synthesis engine. We entered two UK English voices, one built from the full database provided, A, the other from the Arctic subset, B and one Mandarin voice built from the provided database. The evaluation results show that our system provides very good intelligibility, moderate naturalness and low similarity to the original speaker. 1.