It’s true, Amazon Alexa will soon be able to mimic just about any human voice, including lost relatives. All it would need is to hear the voice for less than a minute, whether it be an audio clip or actual voice recording. There’s no word yet on when this feature will be rolling out to devices, but we’re guessing before the holidays.
How is Amazon Alexa able to mimic human voices by just listening to less than a minute of audio? Well, the company made it happen is by framing the problem as a voice-conversion task and not a speech-generation task, without going into further detail. Then we have these audio deepfakes that are very hard to distinguish from real voices.
- MEET ECHO SPOT - A sleek smart alarm clock with Alexa and big vibrant sound. Ready to help you wake up, wind down, and so much more.
- CUSTOMIZABLE SMART CLOCK - See time, weather, and song titles at a glance, control smart home devices, and more. Personalize your display with your...
- BIG VIBRANT SOUND - Enjoy rich sound with clear vocals and deep bass. Just ask Alexa to play music, podcasts, and audiobooks. See song titles and...
These attributes have become even more important during the ongoing pandemic when so many of us have lost ones that we love. While AI can’t eliminate that pain of loss, it can definitely make their memories last,” said Rohit Prasad, senior vice president and head scientist for Alexa.
