'Great tie, I was slag slag Hui ... ...'
Believe this magic words appear in your ears, you will definitely laugh. Indeed, the magic of advertising, circulated in the gossip people laugh, lively atmosphere.
But, have you ever wondered, if this sentence suddenly from the mouth of an animation character you are familiar with, you will be what kind of response?
The development of science and technology, so that life more and more fun, the disguise of the voice, but also to make life more more reversal and mystery. Just a few days ago, held in Chiba Prefecture in Japan Wonder Festival Conference, a The 'Vocal Horn' draws a crowd, and the biggest feature of this 'vocal horn' is that it instantly transforms you into animated characters and magnifies them to make them playable.
AI technology, new applications, fun change sound
This variable-sounding speaker, known as the 'Animegaphone', is colorful and very fancy in appearance, though its distinctive form is the same as normal, but its unique feature is the unique Voice Changer Every time you speak, the speaker will handle the sound and be able to translate it into something that anime characters can say.
The product, which is co-operated by four companies in Japan, TBWA / HAKUHODO, Yukai Engineering, Crimson Technology and KOTOBUKISUN, is designed to arouse, in some cases, such a vocal horn that combines a vocoder and a speaker People pay attention and achieve better guidance.
And this variable sound speaker, its core, is the use of the nowadays most popular AI technology.After the sound has been included in the pre-recorded voice analysis, through 'Real Change Voice' software conversion, your voice will change Into these seiyuu voice.
This technology is different from the general sound-altering technology. The main function of this technology is to change the new sound into the recorded sound by using the AI technology, so as to realize the real sound change.
Fun entertainment market, 'disguise' of the magical experience
It has been a long-held proposition to say that humanity is exploring sound, and people have been trying to reinvent themselves, disguise themselves, disguise their expressions.
And when it comes to using 'AI' technology to 'disguise' the sound, the 'Animegaphone' vocal horn is not unique as early as 2016, Adobe showed a 'Project VoCo' technology developed by Princeton University and Adobe researchers The joint research, which primarily addresses the creation of audiobooks without official support for narration.
This technology, through the machine, attempts to understand the sound composition and generate any discourse as needed.
Then with the help of algorithm, a single phoneme of a person as a material, search and select the appropriate phoneme from the statement to form a new word.
Finally, through the soundtrack into the sound waves, each time a user enters a new word in this tool, the technology can simultaneously update the soundtrack to automatically synthesize new segments of speech.Through technological changes, the use of AI fake sound , Will make the sound more real, more effective.
With the rapid development of science and technology, the market of 'camouflage' will also become a new emerging part of the pan-entertainment culture and become the amusement way for people after gossips.
However, there are also some hidden dangers in the progress of science and technology. How to deal with the social and moral relations in many aspects should also be the issue that we should pay attention to when developing products and entering the market.
Of course, a safer future, it is worth our wait!
