Microsoft is back again with a fantastic technology which is reportedly called “AI neural TTS and holograms.” Let us take a look at it.
AI has been one of the most sought after technologies nowadays. Many companies are doing various researches in this domain to invent some ground-breaking technologies like Google’s Voice Assistant, Amazon’s Alexa, and much more. Now, Microsoft has come up with one such ground-breaking technology which is far more amusing than those mentioned above.
So, what is it all about…?
AI neural TTS and holograms
What if neither distance nor language mattered? What if technology could help you be anywhere you need to be and speak any language? Using AI technology and holographic experiences, this is possible, and it is revolutionary.
This revolutionary technology is unveiled by Julia White (CVP, Azure Marketing) in a demonstration at Microsoft Inspire 2019 in Mandalay Bay Convention Center which is conducted from July 14th, Sunday to July 18th, Thursday with an agenda of unveiling new technologies and describing the company’s vision for the coming year. The event is also graced by several famous speakers Simon Sinek, Rebecca Alexander, and Poly LaBarre.
So, among all the exhibits and speeches, one demonstration that caught the attention of the users is AI neural TTS and holograms.
So, using Azure Hologram AI mechanism, one can be present anywhere as an AI avatar and can speak in the desired language too…!!! Unbelievable, isn’t it…? Well, technology is something which makes unbelievable into believable, thanks to Microsoft’s AI hologram technique and its new update of TTS from Tradition TTS to Neural TTS..
So, How does Microsoft AI hologram work?
So, this azure AI hologram created by Microsoft may remodel somebody into a digital speaker of another language. The software package large disclosed the technology throughout a keynote at the Microsoft Inspire partner conference in Las Vegas.
The main aim of this AI neural TTS and Holograms is to overcome the two hazards for communication, i.e., distance and language. By using this azure AI hologram technique, anyone can be anywhere, speaking any language. Moreover, it seems that Microsoft has become successful in fulfilling its aim.
A demo of this hologram by Microsoft has been shown at Microsoft Inspire 2019. In that demo, Microsoft recently scanned Julia White, a corporation govt for Azure, at a Mixed Reality capture studio to remodel her into a precise photograph duplicate.
The digital version of Julia White arrived onstage to translate the keynote into Japanese. Microsoft has worked its Azure AI technologies and neural text-to-speech to produce this doable. It operates by using recordings of White’s voice, to make a personalized voice signature, to create it sound like she’s speaking Japanese.
With this info collected and sewn along, audience members in Japan employing a HoloLens have watched her keynote in excellent Japanese to recheck she was delivering it right before of them.
In the demo, Julia White said about the new Microsoft azure AI hologram technology – “We are bringing together, the power of Mixed reality and azure AI hologram to create a truly game-changing experience. “
In the demo, the audience witnessed an exact hologram of Julia White wearing the same outfit that had been recently captured at a mixed reality studio. The hologram also translated her keynote from English to Japanese, that too in the same exact voice of Julia White.
In the keynote translated by the hologram, Julia stated that – “We have already seen AI holograms in the past. However, what’s really new in the demo shown today is the translation of my English into Japanese that too in my exact voice.”
This truly fantastic demo involving a new era took all the audience by surprise.
The key technologies used in Microsoft azure AI hologram
The two essential aspects of this technology are – Projection of a life-size hologram of a person, translation of speech from one language to another language. These two features are achieved by two new ground-breaking technologies – Mixed Reality and Neural TTS.
So, let us see what exactly the role of these two technologies in making the magic happen for real.
Mixed Reality and Azure AI Holograms
It is basically a method of virtual teleportation from one space to another regardless of language and distance. Azure Corporate VP, Julia White, said that the “game-changing” experience uses mixed reality and Azure AI services to create the hologram of the speaker.
So, by using this Azure AI Hologram technique, Microsoft is able to create a life-size hologram of the person whose picture was scanned before in a Mixed reality studio. Thus, one part of the task – Projection of a life-size hologram of a person is achieved using Mixed reality and Azure AI holograms.
Neural TTS ( Neural Text-to-speech converter) is used to achieve the translation of the keynote by the hologram in the exact same voice of the actual speaker. The synthesis system uses deep neural networks to overcome the limits of traditional text-to-speech systems for matching stress and intonation patterns in spoken language.
This neural TTS overcomes some drawbacks of the traditional TTS like muffled or buzzy voice when speech units are synthesized into a computer voice. This was due to the mechanism of the traditional TTS, which involves separate prosody into linguistic analysis and acoustic prediction with independent controls.
So, to overcome this drawback in traditional TTS, Neural TTS came up with processing prosody prediction and voice synthesis at the same time, which results in a more fluid and human-like voice.
Commercial availability of this Azure Hologram
Since we have discussed enough the technology aspects of the new AI neural TTS and holograms, let us discuss the possibility of seeing this technology available in the commercial market.
Microsoft has shown off holograms of people before, but the translation aspect in the new Microsoft azure AI hologram is a step beyond what has been possible with HoloLens. It’s unlikely that this most advanced development in Microsoft’s hologram technical school is going to be commercially offered anytime shortly, the probabilities for its use is intriguing because it might have significant effects on communications, travel, and international business.
This looks like it’s just a demonstration for now, and you’d need access to a Mixed Reality capture studio even to start to take advantage of this azure hologram technology. Microsoft’s studios are well equipped with lighting rigs and high-resolution cameras to capture an entirely accurate digital hologram of a person, which isn’t something that can be done easily at home just using a smartphone yet.
So, it will undoubtedly take some years to see this happen at home with a smartphone. But it’s worth waiting for. Apart from the commercial availability, demonstration of the revolutionary technology is pretty impressive from all aspects. So, Microsoft is back with a bang again with its new AI neural TTS and holograms.
We have seen some really unimaginable technologies in the past come alive these days. Let us hope the same with the new Microsoft AI hologram technology.
For now, Microsoft’s new technology is pretty impressive, and it may not target all the users with its initial version. So, it may target businesses first. If there will be any future of version of Microsoft Hololens, then it would undoubtedly have a chance to build software and services that will climb to anywhere augmented reality could end up heading.