Home
List your patent
My account
Help
Support us
Save time and money creating synthetic voices!
[Category : - Audio - Video]
[Viewed 17 times]
METHOD AND APPARATUS FOR DESIGNATING A SOUNDALIKE VOICE TO A TARGET VOICE FROM A DATABASE OF VOICES
A soundalike system to improve speech synthesis by training a text to speech engine on a voice like the target speakers voice.
This patent describes a shortcut for creating synthetic voices (text-to-speech or TTS), making it faster and cheaper to build a high-quality voice model for a new speaker. Foundational for producing new voice models from pre-existing and similar versions.
Here’s how it works:
1 Normally, to synthesize someone’s voice, you need hours of that person’s speech — a big, custom dataset.
2 This system avoids starting from scratch by:
? Searching through a large library of already-modeled voices.
? Finding the one that’s most similar to the new speaker’s voice.
? Using that similar voice model as a starting point (a foundation) for training the new voice.
3 This dramatically reducing how much new voice data is needed — saving time, effort, and money.
[ Home
| List a patent
| Manage your account
| F.A.Q.|Terms of use
| Contact us]
Copyright PatentAuction.com 2004-2017
Page created at 2025-05-08 22:22:32, Patent Auction Time.