The Making of Sophia: Sophia's Singing Voice
17.8 هزار بار بازدید -
5 سال پیش
-
Remember Sophia's duet with Jimmy
Remember Sophia's duet with Jimmy Fallon? To create Sophia's singing voice Hanson Robotics joined up with CereProc, a text to speech (TTS) technology company that creates synthetic voices with character and personality.
The first step was for the woman who made the original recordings for Sophia’s voice to record a number of musical passages at a recording studio. CereProc then built a new database for singing synthesis and trained a Deep Neural Network (DNN) to reproduce the expression, contours, and timbre of the recorded passages.
The resulting model was then able to produce a sequence of musical notes combined with vocal phonemes, which form the sounds necessary to create human speech. To add an extra layer of richness, they used frequency and amplitude modulation to control the pitch and volume of Sophia’s voice, creating a natural-sounding vibrato that brings her performance to life.
To learn more about Sophia's singing, check out our blog post here: https://bit.ly/2Spr1OH
Subscribe to Hanson Robotics: https://bit.ly/2FWnF0M
Follow Sophia the Robot:
Twitter: Twitter: realsophiarobot
Facebook: Facebook: realsophiarobot
Instagram: Instagram: realsophiarobot
LinkedIn: LinkedIn: realsophiarobot
YouTube: https://bit.ly/2RMawys
Follow Hanson Robotics:
Twitter: Twitter: hansonrobotics
Facebook: Facebook: hansonrobotics
Instagram: Instagram: hansonrobotics
LinkedIn: LinkedIn: hanson-robotics
YouTube: https://bit.ly/2FWnF0M
About Hanson Robotics:
Hanson Robotics is an AI and robotics company dedicated to creating empathetic, living, intelligent machines that enrich our lives. Our innovations in AI research and development, robotics engineering, experiential design, storytelling, and material science bring robots to life as engaging characters, useful products, and evolving AI to achieve the ever-greater good for all.
https://www.hansonrobotics.com
The first step was for the woman who made the original recordings for Sophia’s voice to record a number of musical passages at a recording studio. CereProc then built a new database for singing synthesis and trained a Deep Neural Network (DNN) to reproduce the expression, contours, and timbre of the recorded passages.
The resulting model was then able to produce a sequence of musical notes combined with vocal phonemes, which form the sounds necessary to create human speech. To add an extra layer of richness, they used frequency and amplitude modulation to control the pitch and volume of Sophia’s voice, creating a natural-sounding vibrato that brings her performance to life.
To learn more about Sophia's singing, check out our blog post here: https://bit.ly/2Spr1OH
Subscribe to Hanson Robotics: https://bit.ly/2FWnF0M
Follow Sophia the Robot:
Twitter: Twitter: realsophiarobot
Facebook: Facebook: realsophiarobot
Instagram: Instagram: realsophiarobot
LinkedIn: LinkedIn: realsophiarobot
YouTube: https://bit.ly/2RMawys
Follow Hanson Robotics:
Twitter: Twitter: hansonrobotics
Facebook: Facebook: hansonrobotics
Instagram: Instagram: hansonrobotics
LinkedIn: LinkedIn: hanson-robotics
YouTube: https://bit.ly/2FWnF0M
About Hanson Robotics:
Hanson Robotics is an AI and robotics company dedicated to creating empathetic, living, intelligent machines that enrich our lives. Our innovations in AI research and development, robotics engineering, experiential design, storytelling, and material science bring robots to life as engaging characters, useful products, and evolving AI to achieve the ever-greater good for all.
https://www.hansonrobotics.com
5 سال پیش
در تاریخ 1398/11/16 منتشر شده
است.
17,847
بـار بازدید شده