Reading Time: 1.1 min.
Alexa, play American Pie. Alexa, turn down the volume, find a Greek restaurant, and order the dog food. The number of tasks we entrust today to the Amazon digital assistant is enormous. And soon, thanks to its new audio synthesizer function, it will help you hear the voice of your loved ones.
During Amazon’s annual re:Mars event, the company announced a new feature that can synthesize short audio clips into longer clips. According to TechCrunch, one scenario featured at the conference was the voice of a deceased loved one; specifically, a grandmother is used to reading a bedtime story to a grandchild. Amazon’s Senior Vice President and Chief Scientist for Alexa, Rohit Prasad, said that using the new technology, Amazon can turn a minute of conversation into endless possibilities.
This required inventions where we had to learn to produce a high-quality voice with less than a minute of the recording versus hours of recording in the studio. We achieved this by framing the problem as a voice conversion task. And not as a speech generation pathway. Without a doubt, we live in the golden age of AI, where our dreams and science fiction are becoming a reality, says Prasad.
In addition, they are working on Alexa to make her more human. The company is opting for a more think before you speak approach, where Alexa would use implicit common sense knowledge to generate responses. For example, if a customer on Valentine’s Day asked, Alexa, I want to buy flowers for my wife, it would answer: Maybe, you should buy her red roses.
Amazon hasn’t revealed a timeline for when we can expect this feature to roll out; the executive stated that they are working on it.
Share
Images
Unsplash @elodiso, @jankolar, @grantritchie.
