Multisyn Voice for the Blizzard Challenge 2006
نویسندگان
چکیده
This paper describes the process of building unit selection voices for the Festival Multisyn engine using the ATR dataset provided for the Blizzard Challenge 2006. We begin by discussing recent improvements that we have made to the Multisyn voice building process, prompted by our participation in the Blizzard Challenge 2006. We then go on to discuss our interpretation of the results observed. Finally, we conclude with some comments and suggestions for the formulation of future Blizzard Challenges.
منابع مشابه
Festival Multisyn Voices for the 2007 Blizzard Challenge
This paper describes selected aspects of the Festival Multisyn entry to the Blizzard Challenge 2007. We provide an overview of the process of building the three required voices from the speech data provided. This paper focuses on new features of Multisyn which are currently under development and which have been employed in the system used for this Blizzard Challenge. These differences are the a...
متن کاملMultisyn voices from ARCTIC data for the blizzard challenge
This paper describes the process of building unit selection voices for the Festival multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build procedure is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for buil...
متن کاملMultisyn Voices from ARCTIC Data f
This paper describes the process of building unit selection voices for the Festival multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build procedure is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for buil...
متن کاملUSTC System for Blizzard Challenge 2006 an Improved HMM-based Speech Synthesis Method
This paper introduces the USTC speech synthesis system for Blizzard Challenge 2006. The HMM-based parametric synthesis approach was adopted for its convenience and effectiveness in building a new voice, especially for the nonnative developers. Some useful techniques were also integrated into our system, such as minimum generation error (MGE) training, phone duration modeling and linear spectral...
متن کاملNTTS participation in the Blizzard Challenge 2008-v2
This paper describes NTTS participation in the Blizzard Challenge 2008. The Blizzard Challenge 2008 extended the evaluation languages to Mandarin. In this year, the basic NTTS system was updated with a new Mandarin phrase prediction module. According to the listening evaluation results, all three aspects of English voice, similarity, MOS and word error rate, have been improved slightly. However...
متن کامل