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 |
---|
Paradigms |
Problems
|
Supervised learning (classification • regression) |
Clustering |
Dimensionality reduction |
Structured prediction |
Anomaly detection |
Artificial neural network |
Reinforcement learning |
Learning with humans |
Model diagnostics |
Mathematical foundations |
Journals and conferences |
Related articles |
VALL-E is a generative artificial intelligence system for speech synthesis developed by Microsoft Research and announced on January 5, 2023. It can "recreate any voice from a three-second sample clip". It has been trained on 60,000 hours of English language speech from Meta’s audio library LibriLight.
See also
- Amazon Polly
- Audio deepfake
- Comparison of speech synthesizers
- Deep learning speech synthesis
- Natural language generation
- Speechify
- Voice phishing
- Zero-shot learning
External links
References
- 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 Misplaced Pages by expanding it. |
This article about software created, produced or developed by Microsoft is a stub. You can help Misplaced Pages by expanding it. |
Speech synthesis | |||||
---|---|---|---|---|---|
Free software |
| ||||
Proprietary software |
| ||||
Machine | |||||
Applications | |||||
Protocols | |||||
Developers/ Researchers | |||||
Process |