Video Credits: Aflorithmic, YouTube
Artificial Intelligence (AI) has been fundamental in various breakthroughs and discoveries. From medical to construction, restaurant to agriculture this technology has been assisting for better results and productivity. Just when we thought AI could not get any better, two companies have now brought Albert Einstein’s voice to life with the help of Artificial Intelligence (AI).
Alforithmic is an audio content production company. UneeQ is the digital human creator company. Both of these companies have collaborated in order to synthesize Albert Einstein’s voice.
In order to create this synthesization of Albert Einstein’s voice, UneeQ combined the visual character rendering techniques along with an advanced computational knowledge engine. This was done to make the prototype sound as realistic as possible.
Matt Lehman, the COO of Alforithmic said, “This is the next milestone in showcasing the technology to make conversational social commerce possible. There are still more than one flaws to iron out as well as tech challenges to overcome but overall we think this is a good way to show where this is moving to.”
This project will be able to provide its users with an opportunity to ask this Einstein AI practical questions. It will be able to give them a feeling as if they are interacting with the scientist in real life. The reason why both these companies chose Albert Einstein was due to the scientist’s popularity and that he is vastly regarded as a genius icon.
With such an extremely historical figure coming to ‘life’, the companies claim that they see a huge educational potential in this project. The company Alforithmic said that they worked with a voice actor to do voice modelling for the chatbot. The company also says that this ‘digital Einstein’ is just a showcase for what will soon be possible will conversational social commerce.
In order to acquire the authenticity in the base of Albert Einstein’s voice the researchers has to go through historical records. Such records describe Albert Einstein’s voice was heavy with German accent and he used to speak slowly, kindly and wisely in a high pitched voice.
Due to the poor quality of the recordings which were available and referred to by the team of researchers and also the thick accent in which Albert Einstein used to speak, it was difficult for the development team to capture a solid frame of reference in order to understand how he must have exactly sounded.
The researchers then built a bot whose voice was not the same but as close to reality as possible as the researchers assumed that the users of this bot will not worry much about the accuracy of the voice while using it.
In order to make it as real life like possible this bot will be able to communicate with the users using the same thick heavy German accent which Albert Einstein used to speak with. Along with that the bot will also accompany some elements of dry humour as well as friendliness which the scientist used to speak with.
The researchers were successful in providing this Artificial Intelligence (AI) bot the ability to speak as if it is reflecting upon his own knowledge while interacting with the users. With the help of a computational knowledge engine to Aflorithmic’s API Einstein bot’s response time is less than three seconds.