“Hey, Alexa, what’s another word for ‘scary’?”
In a demonstration that compared the dystopian series “Black Mirror”, Amazon revealed that it has developed a way for its voice assistant Alexa to replicate the speech of a dead relative – based on less than a minute recorded audio of the original man.
The e-commerce giant unveiled the new technology at its re: MARS conference on Wednesday, Amazon’s global artificial intelligence event for machine learning, automation, robotics and space. In a video demonstration shown at the event, a young boy says, “Alexa, can Grandma read me The Wizard of Oz?”
“As you saw in this experience, instead of the voice of Alexa reading the book, it is the voice of the child’s grandmother,” said Rohit Prasad, Alexa AI’s senior vice president and chief scientist.
Amazon has already developed voice synthesis technology to allow Alexa to mimic the voices of celebrities, including Shaquille O’Neill and Melissa McCarthy. But that used to require a person to record dozens of hours of audio. Amazon has now developed a way to reproduce high-quality voice using less than a minute of recorded speech, which the company’s engineers have been able to do “by shaping the problem as a voice conversion task, not a speech generation task.” according to Prasad.
Presenting the demo, Prasad said that Alexa’s AI ability to emulate the speech of a deceased relative could be a way to preserve the memory of a loved one who has died. “Undoubtedly we live in the golden age of AI, where our dreams and science fiction are becoming a reality,” he said.
Watch the Alexa demo in the video below:
additional screen reader
Add Comment