Vale software
Vale software |
This software is adept at simulating not only voice but also emotional tones and fluctuations.
60,000 hours of speech in English by 7,000 people were used to create the VALLE language model to synthesize any unseen person's 'high-quality speech'.
When the software has only one voice recording of a person, the system can make the person say anything they want.
It can copy the voice and the person's emotional tone and acoustic environment.
It should be noted that like the deep fake technology that mimics a person's visual resemblance in videos, it also has the potential to be misused.
Microsoft has stated that 'VALE software used to simulate voice is used to simulate voice,' citing other concerns, including potential risks if the model is misused, such as voice spoofing or simulating a speaker. The vale software is not available for public use
No comments
If you want to know many more, please let me know