Amazon’s Alexa voice assistant is ready to imitate the voices of the lifeless, consistent with Rohit Prasad, Amazon senior vp and hHead scientist for Alexa.
Prasad, all through the corporate’s re:MARS convention in Las Vegas on Wednesday, described Alexa’s capacity to “synthesize quick audio clips” and create speech from them, TechCrunch reported.
In his speech, Prasad mentioned how a lifeless grandmother’s voice might be used to learn their surviving kid a tale at night time, consistent with TechCrunch.
“This required innovations the place we needed to learn how to produce a top quality voice with not up to a minute of recording as opposed to hours of recording within the studio,” Prasad stated.
“The way in which we made it occur is by means of framing the issue as a voice conversion activity and now not a speech technology trail. We’re indubitably residing within the golden technology of AI, the place our desires and science fictions are changing into a fact.”
Main points are unclear as to when the corporate will introduce the era to Alexa, Reuters reported, however Prasad stated its purpose is to “make reminiscences remaining,” making an allowance for the tens of millions who’ve misplaced family members within the COVID-19 pandemic.