Jump to content

VALL-E

From Wikipedia, the free encyclopedia

VALL-E
Developer(s)Microsoft
PlatformCloud computing platforms
Websitehttps://www.microsoft.com/en-us/research/project/vall-e-x/

VALL-E is a generative artificial intelligence system for speech synthesis developed by Microsoft Research and announced on January 5, 2023.[1] It can "recreate any voice from a three-second sample clip".[2] It has been trained on 60,000 hours of English language speech from Meta’s audio library LibriLight.[3]

See also

[edit]
[edit]

References

[edit]
  1. ^ Dominguez, Daniel (January 27, 2023). "Microsoft Unveils VALL-E, a Game-Changing TTS Language Model". InfoQ. Retrieved September 19, 2023.
  2. ^ Morrison, Ryan (January 10, 2023). "Microsoft's new VALL-E AI can clone your voice from a three-second audio clip". Tech Monitor. Retrieved September 19, 2023.
  3. ^ Wodecki, Ben (January 11, 2023). "Microsoft's VALL-E Generates Speech From Just 3 Seconds of Audio". AI Business.