Blizzard Challenge: Difference between revisions
From SynSIG
Simon.King (talk | contribs) No edit summary |
m (clean wikilink) |
||
Line 1: | Line 1: | ||
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. | 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. | ||
This is now a regular series of challenges. The latest one is the [[ | This is now a regular series of challenges. The latest one is the [[Blizzard Challenge 2007]]. Descriptions of, and publications from, previous challenges can currently be found on [http://festvox.org/blizzard the Festvox site]. |
Revision as of 14:54, 16 February 2007
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.
This is now a regular series of challenges. The latest one is the Blizzard Challenge 2007. Descriptions of, and publications from, previous challenges can currently be found on the Festvox site.