VALL-E
| Developer(s) | Microsoft |
|---|---|
| Platform | Cloud computing platforms |
| Website | https://www.microsoft.com/en-us/research/project/vall-e-x/ |
| Part of a series on |
| Machine learning and data mining |
|---|
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]- Amazon Polly
- Audio deepfake
- Comparison of speech synthesizers
- Deep learning speech synthesis
- Natural language generation
- Speechify
- Voice phishing
- Zero-shot learning
External links
[edit]References
[edit]- ^ Dominguez, Daniel (January 27, 2023). "Microsoft Unveils VALL-E, a Game-Changing TTS Language Model". InfoQ. Retrieved September 19, 2023.
- ^ 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.
- ^ Wodecki, Ben (January 11, 2023). "Microsoft's VALL-E Generates Speech From Just 3 Seconds of Audio". AI Business.
 | This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it. |
 | This article about software created, produced or developed by Microsoft is a stub. You can help Wikipedia by expanding it. |