The DRESS Blizzard Challenge 2008 Entry
نویسندگان
چکیده
This paper presents the version of the DRESS System that participated in the Blizzard Challenge 2008. Here we show a basic overview of the DRESS system, methodology and a description of its unit selection. We present a novel concept to increase the efficiency of the exhaustive speech unit search within the database by an unit selection model that is based on mapping analysis of the concatenation costs and Bayes optimal classification (BOC).
منابع مشابه
The AHOLAB Blizzard Challenge 2008 Entry
This paper describes the process of building unit selection voices for our participation in the Blizzard Challenge 2008. Out of the three voices required (15 hours UK English, 1 hour UK English subset and 6.5 hours Mandarin Chinese) we only built the English ones.
متن کاملThe MARY TTS entry in the Blizzard Challenge 2008
The present paper reports on the DFKI entry to the Blizzard challenge 2008. The main difference of our system compared to last year is a new join model inspired by last year’s iFlytek paper; the effect seems small, but measurable in the sense that it leads to the selection of longer chunks of consecutive units. In interpreting the results of the listening test, we correlate the ratings to vario...
متن کاملAn Overview of the VUB Entry for the 2008 Blizzard Challenge
In this paper, we describe the configuration of our synthesizer, as used for the Blizzard Challenge the first time. Two new UK English voices were built for the DSSP synthesizer, our in-house unit selection synthesizer, which uses non-uniform units and a symbolic description of target prosody. Listening tests indicate reasonable quality although there is still room for improvement.
متن کاملStatistical 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, the other from the Arctic subset, B and one Mandarin voice built from the provided database. Th...
متن کاملThe Jess Blizzard Challenge 2007 Entry
The Blizzard Challenge is an independent evaluation of synthetic speech systems. This paper describes the Jess system, one of the participants in the Blizzard Challenge 2007. One of the unique features of the Jess system is the use of articulatoryacoustic feature detection to ensure a higher degree of acoustic consistency at joins. To make results comparable with the system presented last year ...
متن کامل