Tech
Microsoft announces text-to-speech AI model VALL-E, which is trained on English speech data and can simulate a person’s voice with three seconds of sample audio (Benj Edwards/Ars Technica)
Benj Edwards / Ars technique:
Microsoft unveils VALL-E text-to-speech AI model, which is trained on English speech data and can simulate a person’s voice with three seconds of sample audio— The text-to-speech model can preserve the emotional tone and acoustic environment of the speaker. — On Thursday, Microsoft researchers announced…
Source by [author_name]