What if he accidentally became a tech superstar?
6 Leading global voice technology

A High Mon

Settings
ScrollingScrolling

Chen Yao installed the programming software immediately.

This programming software called " Universe " was found from a black technology USB drive. It could speed up programming.

When writing code, it would provide you with intelligent associations, intelligent supplements, and intelligent repairs.

The overtime code did not exist, and the Bug did not exist.

There were plenty of dubbing software on the internet. Professional film companies also had their own dubbing software, and the effects were very good.

What was so awesome about Chen Yao's dark horse voice acting?

In a word, AI voice dubbing!

To put it bluntly, it was to use artificial intelligence voice to replace the dubbing artist to complete the dubbing of movies and animations.

Such intelligent dubbing technology, let alone in China, no company in the world could do it.

This was because it involved a very complicated " natural voice recognition " technology!

In China, Baidu and Xunfei were undoubtedly the most advanced in the field of " natural voice " technology. Many people used the voice input methods of the two companies. The technology behind them came from their powerful AI voice recognition engine.

In foreign countries, the most powerful voice technology was Amazon, Google, and Microsoft.Many people had played with Microsoft.com.

These companies were already the most cutting-edge technology companies in the world, but they still couldn't make real intelligent dubbing software.

If he wanted to make the intelligent voice to complete the dubbing of movies and animations like a real person, he needed to solve two major problems.

First, it was extremely intelligent.

To put it bluntly, the so-called artificial intelligence of today was a little stupid.

Smart slightly. If you ask a question to the smart speaker, the answer will often be funny.

For example, if you ask the smart slightly," There's a 5-yuan bill and a 100-yuan bill at your feet. Which one would you pick up?”

The voice assistant's answer was either " I don't know.”Or answer,"Pick up 100 yuan."”

The correct answer should be, I picked up both!

Then, he asked the smart slightly," I'm driving on the road. Suddenly, a person rushed out from the left and a dog rushed out from the right. Should the car turn left or right?”

The smart slightly would answer that it didn't know or that it was turning right.

The real answer should be to brake!

The so-called artificial intelligence now gave people the feeling that it was a retard, or a blockhead.

All the questions and answers were set up by the programmers behind the scenes, not by real neural network intelligence.

The so-called deep learning could not be flexible.

For example, ask him a brain teaser.

Xiao Ming's father has four sons. The eldest son is called Da Ming, the second son is called Er Ming, and the third son is called San Ming. What's the name of the fourth son?

The voice assistant would answer according to the logical algorithm,""Siming!"

There was something called big data. The programmer could collect all the brain teasers. Then, wouldn't the smart slightly be able to answer the questions correctly?

However, if I were to ask in a different way...

There was a man called Silly Pen. Silly Pen's father had three sons. The eldest son was called Big Pen, the second son was called Er Pen, and what was the name of the third son?

Then, the smart slightly wouldn't answer again. It either didn't know or was spouting nonsense.

Although dubbing didn't require a high IQ, nor did it need to answer questions, it still needed to have the ability to distinguish images.

When dubbing for movies and anime, the dubbing artist had to adjust the tone and intonation according to the scene and the expressions of the characters.

Nowadays, artificial intelligence was very good at Optical Character Recognition and could basically achieve 100%. Even robots could dub when watching movie subtitles.

But the problem was…

If he couldn't recognize the scenes and expressions in the movie, the effect would be very bad.

In terms of dynamic image recognition, no company in the world was really good at it.

The second problem was the emotions of the artificial voice.

The voice of a real person was full of cadence, joy, anger, sadness, breathing, and saliva. The rhythm was fast or slow. Such a dubbing effect was impossible to achieve with today's voice.

Nowadays, the voice was electronic and metallic. Although some companies made the voice very realistic, one could still clearly hear the impersonal " robot " voice.

The same sentence would have different effects in different scenes.

Happy!

"If I can't get your love in this life, I'll meet you again in the next life.”The female lead found the male lead at the scene of the disaster. He was still alive, and her tone was happy.

Furious!

"If I can't get your love in this life, I'll meet you again in the next life.”The villain was stabbed in the chest by the female protagonist. His tone was filled with anger and unwillingness.

Sad!

"If I can't get your love in this life, I'll meet you again in the next life.”The male lead confessed to the female lead and was rejected. His tone was downcast.

Happy!

"If I can't get your love in this life, I'll meet you again in the next life.”The male lead succeeded in teasing the female lead on April Fool's Day, and he laughed proudly.

A live voice actor could produce different effects according to different scenes.

The AI voice could only be dubed according to the text. Every time it spoke, its tone and intonation were the same.

Such a dull voice could not be used in the dubbing of movies and animations.

Therefore, if artificial intelligence was to be used in the field of dubbing, it would have to make a revolutionary leap in terms of intelligence and true emotions.

There was no company in the world that could do it well, and this was an opportunity for start-ups.

Chen Yao's fingers quickly typed on the keyboard, and a string of codes appeared in the edit box.

His brain and hand speed had been enhanced by black technology, so his typing speed was godlike.

In the blink of an eye, 20 lines of code…In the blink of an eye, 50 lines of code…

If it was an ordinary person, not to mention having his hand speed, even his eyes wouldn't be able to move so fast. Before he could see what was written, he would quickly scroll and refresh the screen.

Chen Yao was completely immersed in the realm of programming, experiencing the lightning-like refreshing pleasure.

About three hours later…

"Pa!" " Okay!" Chen Yao hit the enter key heavily." It's done!"”

The Dark Horse dubbing software was successfully developed!

What was even more powerful was its built-in intelligent voice engine. The former did not have a lot of tasks, and most of the time was spent on the voice engine.

The bottom layer of the voice engine was the world's first truly intelligent neural network framework. The complexity of the algorithm was comparable to the human brain.

If it were Google or Microsoft.com, it would take at least 20 years to make it.

Chen Yao rubbed his fingers." I spent three hours. I'm so tired."”

Apart from his own speed, there was another reason why it was so fast. Many of the data inside came from the universal USB drive and were directly imported, saving a lot of effort.

Originally, Chen Yao wanted to find the finished dubbing software directly in the USB drive so that he did not have to write the code himself.

However, the USB drive had only unlocked the first Aries partition. This partition was not a finished product. To unlock the other partition required more points.

Actually, on second thought, it was good to have him participate in the writing of the Dark Horse dubbing software. It would give him a greater sense of accomplishment. Anyway, it wouldn't take much time.

Now that he had the dubbing software and the voice engine, the next step was to produce vocal characters.

This book is provided by FunNovel Novel Book | Fan Fiction Novel [Beautiful Free Novel Book]

Last Next Contents
Bookshelf ADD Settings
Reviews Add a review
Chapter loading