The blizzard challenge 2005 CMU entry - a method for improving speech synthesis systems
نویسندگان
چکیده
In CMU's Blizzard Challenge 2005 entry we investigated twelve ideas for improving Festival-based unit selection voices. We tracked progress by adopting a 3-tiered strategy in which candidate ideas must pass through three stages of listening tests to warrant inclusion in the final build. This allowed us to evaluate ideas consistently without us having large human resources at our disposal, and thereby improve upon our baseline system within a short amount of time.
منابع مشابه
The Blizzard Challenge 2006 CMU Entry introducing hybrid trajectory-selection synthesis
Acknowledging the lessons of Blizzard Challenge 2005 – that smooth prosodic cadence supersedes spectral resolution – but wanting a system devoid of vocoding artifacts – we introduce a hybrid trajectory-selection synthesizer. Using a parametric synthesizer to generate a pitch-synchronous sequence of F0/duration/power and spectral vectors, this trajectory serves as the target cost function for a ...
متن کاملThe CSTR entry to the Blizzard Challenge 2016
This paper describes the text-to-speech system entered by The Centre for Speech Technology Research into the 2016 Blizzard Challenge. This system is a hybrid synthesis system which uses output from a recurrent neural network to drive a unit selection synthesiser. The annual Blizzard Challenge conducts side-byside testing of a number of speech synthesis systems trained on a common set of speech ...
متن کاملOn building a concatenative speech synthesis system from the blizzard challenge speech databases
In this paper, we compare two methods of building a concatenative speech synthesis system from the relatively small, “Blizzard Challenge” speech databases. In the first method we build a system directly from the Blizzard databases using the IBM Concatenetative Speech Synthesis System originally designed for very large speech databases. In the second method, a larger database is used to build th...
متن کاملThe blizzard challenge - 2005: evaluating corpus-based speech synthesis on common datasets
In order to better understand different speech synthesis techniques on a common dataset, we devised a challenge that will help us better compare research techniques in building corpusbased speech synthesizers. In 2004, we released the first two 1200-utterance single-speaker databases from the CMU ARCTIC speech databases, and challenged current groups working in speech synthesis around the world...
متن کاملThe NII speech synthesis entry for Blizzard Challenge 2016
This paper decribes the NII speech synthesis entry for Blizzard Challenge 2016, where the task was to build a voice from audiobook data. The synthesis system is built using the NII parametric speech synthesis framework that utilizes Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) for acoustic modeling. For this entry, we first built a voice using a large data set, and then used the...
متن کامل