will talk to one side about the other. but first, nick kwek has been looking at how peter 2.0 has been realised. today, i m in the scottish capital of edinburgh, a city with a rich history of storytelling, where novel ideas come to life and the art of discourse has been mastered. i m here to meet the engineers putting personality into synthetic voice. voice is part of what we are, it s part of our souls, it s the way we communicate, it betrays where we re from, our emotions, our motives, everything. dr matthew aylett and his team have been banking peter s voice so that peter can continue to talk now it is gone. he had to have his vocal tract removed, so before that happened, we recorded him extensively and then we were able to recreate his voice in a speech synthesis system so he can now type in text and it will speak
but first, nick kwek has been looking at how peter 2.0 has been realised. today, i m in the scottish capital of edinburgh, a city with a rich history of storytelling, where novel ideas come to life and the art of discourse has been mastered. i m here to meet the engineers putting personality into synthetic voice. voice is part of what we are, it s part of our souls, it s the way we communicate, it betrays where we are from, our emotions, our motives, everything. dr matthew aylett and his team have been banking peter s voice so that peter can continue to talk now it is gone. he had to have his vocal track removed, so before that happened, we recorded him extensively and then we were able to recreate his voice in a speech synthesis system so he can now type in text and it will speak exactly the way that he used to speak. text to speech technology has been around for a while.
but first, nick kwek has been looking at how peter 2.0 has been realised. today, i m in the scottish capital of edinburgh a city with a rich history of storytelling, where novel ideas come to life and the art of discourse has been mastered. i m here to meet the engineers putting personality into synthetic voice. voice is part of what we are, it s part of our souls, it s the way we communicate, it betrays where we are from, our emotions, our motives, everything. doctor matthew aylett and his team have been banking peter s voice so that peter can continue to talk now it is gone. he had to have his vocal track removed, so before that happened, we recorded him extensively and then we were able to recreate his voice in a speech synthesis system so he can now type in text and it will speak exactly the way that he spoke. text to speech technology has been around for a while.
first, nick has been looking at how peter 2.0 has been realised. how peter 2.0 has been realised. ., realised. today i m in the scottish realised. today i m in the scottish capital, - realised. today i m in the l scottish capital, edinburgh, realised. today i m in the - scottish capital, edinburgh, a city with a rich history of storytelling, where novel ideas come to life and the art of this course has been mastered. i m here to meet engineers putting personality into synthetic hearts. voice is part of what we are, part of our soul, the way we communicate, betrays where from, emotions, motives, everything. motives, everything. doctor matthew elliott motives, everything. doctor matthew elliott and - motives, everything. doctor matthew elliott and his - motives, everything. doctor| matthew elliott and his team have been banking peter s voice so that he can continue to talk when it is gone. he so that he can continue to talk when it is gone. so that he can continue to talk when i
when it is gone. he had to have his vocal track removed, so before that happened we recorded him extensively and we were able to recreate his voice in a speech synthesis system so that he can now type in text and it will speak exactly the way that he spoke. text to speech technology has been around for a while. all remember microsoft sam, right? peter provided far more than the average voice sample recording. 15 hours worth of material. in order to make a voice you take the audio and you use a system to learn how the sounds in the voice relate to the words that are being spoken. once you have that model built you can put a new set of words in and it will produce a new output with that voice. to convey sentiment for specific scenarios, peter captured himself speaking in four different styles. the tone of voice is very important.