In order to better understand and compare research techniques in building corpus-based speech synthesizers on the same data, the Blizzard Challenge has been devised.

The basic challenge is to take the released speech database, build a synthetic voice from the data and synthesize a prescribed set of test sentences. The sentences from each synthesizer will then be evaluated through listening tests.

Blizzard Challenge 2022 is current under development.

Results from previous Challenges:

• Blizzard Challenge 2021 papers and results
• Blizzard Challenge 2020 papers and results
• Blizzard Challenge 2019 papers and results
• Blizzard Challenge 2018 papers and results
• Blizzard Challenge 2017 papers and results
• Blizzard Challenge 2016 papers and results
• Blizzard Challenge 2015 papers and results
• Blizzard Challenge 2014 papers and results
• Blizzard Challenge 2013 papers and results
• Blizzard Challenge 2012 papers and results
• Blizzard Challenge 2011 papers and results
• Blizzard Challenge 2010 papers and results
• Blizzard Challenge 2009 papers and results
• Blizzard Challenge 2008 papers and results
• Blizzard Challenge 2007 papers and results
• Blizzard Challenge 2006 papers and results
• Blizzard Challenge 2005 papers and results

For further information please contact blizzard@festvox.org

Further description of the Challenge itself was published in Interspeech 2005 Eurospeech in Lisbon: http://www.festvox.org/blizzard/bc2005/IS051946.PDF