Amazon’s Alexa voice assistant is ready to imitate the voices of the lifeless, in line with Rohit Prasad, Amazon’s senior vice chairman and hHead scientist for Alexa.
Prasad, in the course of the firm’s re:MARS convention in Las Vegas on Wednesday, described Alexa’s functionality to “synthesize brief audio clips” and create speech from them, TechCrunch reported.
In his speech, Prasad mentioned how a lifeless grandmother’s voice could possibly be used to learn their surviving youngster a narrative at night time, in line with TechCrunch.
“This required innovations the place we needed to be taught to provide a high-quality voice with lower than a minute of recording versus hours of recording within the studio,” Prasad stated.
“The way in which we made it occur is by framing the issue as a voice conversion process and never a speech era path. We’re unquestionably dwelling within the golden period of AI, the place our goals and science fictions have gotten a actuality.”
Particulars are unclear as to when the corporate will introduce the know-how to Alexa, Reuters reported, however Prasad stated its objective is to “make reminiscences final,” contemplating the thousands and thousands who’ve misplaced family members within the COVID-19 pandemic.