In this paper we describe the voices we submitted to the 2009 Blizzard Challenge, a yearly challenge to evaluate auditory speech synthesis on common data. Since it is the second time we participate in this challenge, in this paper we focus on the changes we made to our unit selection-based system. The weighted sum of symbolic target costs has been replaced by a single statistical target cost; the weighted sum of acoustic join cost has been replaced by a single statistical join cost. Both these costs are based on context-clustering decision tree modeling, and trained on the speech database. Furthermore, the voice building process has been enhanced by improving the segmentation quality and by automatically removing potentially {"}bad{"} units.
Latacz, L, Mattheyses, W & Verhelst, W 2009, The VUB Blizzard Challenge 2009 Entry. in Blizzard Challenge 2009, Edinburgh, United Kingdom. Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet, Stockholm, Sweden, 21/09/09. <http://www.festvox.org/blizzard/bc2009/vub_Blizzard2009.pdf>
Latacz, L., Mattheyses, W., & Verhelst, W. (2009). The VUB Blizzard Challenge 2009 Entry. In Blizzard Challenge 2009, Edinburgh, United Kingdom http://www.festvox.org/blizzard/bc2009/vub_Blizzard2009.pdf
@inproceedings{91bf4fe906194284ac47fb7d9b7ef99b,
title = "The VUB Blizzard Challenge 2009 Entry",
abstract = "In this paper we describe the voices we submitted to the 2009 Blizzard Challenge, a yearly challenge to evaluate auditory speech synthesis on common data. Since it is the second time we participate in this challenge, in this paper we focus on the changes we made to our unit selection-based system. The weighted sum of symbolic target costs has been replaced by a single statistical target cost; the weighted sum of acoustic join cost has been replaced by a single statistical join cost. Both these costs are based on context-clustering decision tree modeling, and trained on the speech database. Furthermore, the voice building process has been enhanced by improving the segmentation quality and by automatically removing potentially {"}bad{"} units.",
keywords = "speech synthesis, unit selection, statistical selection costs",
author = "Lukas Latacz and Wesley Mattheyses and Werner Verhelst",
year = "2009",
month = sep,
day = "4",
language = "English",
booktitle = "Blizzard Challenge 2009, Edinburgh, United Kingdom",
note = "Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet ; Conference date: 21-09-2009 Through 25-09-2009",
}