As soon as possible, Chen Yao installed programming software.

This programming software called "Universal" was found from the black technology USB drive. Using it, it can speed up programming.

When writing code, it will give you intelligent association, intelligent supplementation, and intelligent repair.

The 996 overtime code code does not exist, and the bug does not exist.

When it comes to dubbing software, you can search it online and have a lot of professional film companies. They also have their own professional dubbing software, and the effect is also very good.

What is the awesomeness of the dark horse dubbing developed by Chen Yao?

A summary of one sentence - AI intelligent dubbing!

To put it bluntly, it is to use artificial intelligence voice to replace the voiceover of the voice actors to complete the dubbing of movies and animations.

Such intelligent dubbing technology, not to mention that no company in the world can do it.

Because, there is a very complex "natural speech recognition" technology involved!

In China, Baidu and iFlytek are undoubtedly the most advanced in their "natural voice" technology. Many people use the voice input methods of both companies. The technology behind them comes from their powerful AI voice recognition engine.

In foreign countries, the most powerful voice technology is Amazon, Google, Microsoft, and Microsoft Xiaobing. Many people have played it.

These companies are already the most cutting-edge technology companies in the world today, but they still cannot make real smart dubbing software.

If you want to make smart voice complete the dubbing of movies and anime like a live person, two major problems need to be solved.

First, super high intelligence.

The so-called artificial intelligence today, to put it bluntly, is really a bit stupid.

Smart speakers, when you ask questions to smart speakers, the answers often make people feel ridiculous.

For example, you ask the smart speaker: "With a 5 yuan and a 100 yuan bill under your feet, which one would you pick up?"

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

The correct answer should be: I picked up both pictures!

Ask the smart speaker again: "Driving on the road, suddenly a person rushed out of the left and a dog rushed out of the right. Should the car turn left or right?"

The smart speaker will answer that you don’t know, or turn right.

The real answer should be: brakes!

The so-called artificial intelligence today gives people a more mentally retarded or a stubborn fool.

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

The so-called deep learning cannot be flexible and flexible.

For example, ask him a brain teaser.

Xiao Ming's father has four sons. The eldest son is called Daming, the second son is called Erming, the third son is called Sanming, and what is the fourth son's name?

The voice assistant will answer according to the logical algorithm: "Siming!"

There is a thing called big data, which programmers can collect all brain teasers. In that case, can't the smart speaker answer the above questions correctly?

But if I change the way to inquire.

There is a man named Shabi. Shabi's father has three sons. The eldest son is called Dabi, the second son is called Erbi, and what is the third son's name?

Then the smart speaker will not answer, either don’t know or talk nonsense.

Although dubbing does not require any high IQ or it does not need to answer questions, it must at least have image resolution capabilities.

When dubbing movies and anime, the voiceover needs to adjust the tone and tone of speech based on the scenes inside, the expressions of the characters, etc.

Today's artificial intelligence is very strong in text recognition, and can basically achieve 100%. When watching movie subtitles, robots can also dub.

But the problem is...

If you cannot recognize the scenes and expressions in the movies and anime, the effect will be very poor.

When it comes to dynamic image recognition, no company in the world is really doing well.

The second problem is the emotionality of artificial voice.

The voice of a real person speaking is ups and downs, joy, anger, sorrow, and happiness, breathing, saliva, and a fast or slow rhythm. Such dubbing effects are something that today's voice cannot achieve.

Nowadays, voice is electronic sound and metal sound. Although the voice made by some companies is very realistic, it is still obvious that the inhuman "robot" sound can be heard.

The same sentence will have different performance effects in different film, television and animation scenes.

happiness!

"If you can't get your love in this life, you will meet again in the next life." The heroine found the hero at the scene of the disaster. He is still alive, and her tone is joyful.

anger!

"If you can't get your love in this life, you will meet again in the next life." The villain was pierced by the heroine's chest with a sword, and his tone was full of anger and reluctance.

sorrow!

"If you can't get your love in this life, you will meet again in the next life." The male protagonist confessed to the female protagonist, but was rejected, and his tone was depressed.

happy!

"I won't get your love in this life, and I will meet again in the next life." The male protagonist successfully teased the heroine on April Fools' Day, and he laughed proudly.

Live dubbing can show different dubbing effects according to different scenes.

AI voice can only be dubbed based on text. Every time it is said, its tone and tone are the same, the same.

Such a dull voice is impossible to use in film, television, animation and dubbing.

Therefore, if artificial intelligence wants to be applied in the field of dubbing, it must make a revolutionary leap in intelligence and true feelings.

There is no company in the world that can do it well, and this is the opportunity left to start-ups.

Chen Yao quickly typed his fingers on the keyboard, and a string of codes appeared in the editing box.

His brain and hand speed have been strengthened by black technology, and his typing speed is so fast.

The time to blink, 20 lines of code... The time to blink, 50 lines of code...

If it were an ordinary person, not to mention his hand speed, his eyes would not be as fast as he did. Before he could see what he wrote clearly, the screen was quickly rolling and refreshing.

Chen Yao was completely immersed in the realm of writing programs and experiencing the refreshing pleasure like lightning.

About three hours later...

"Bang!" Chen Yao hit the Enter key repeatedly: "OK, the job is done!"

The development of dark horse dubbing software has been successful!

What's more powerful is its built-in intelligent voice engine. The former's task is not large and most of the time is spent on the voice engine.

The bottom layer of the voice engine is the first intelligent neural network framework in the world today, and the complexity of the algorithm is comparable to that of the human brain nerves.

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

Chen Yao rubbed his fingers: "It took me 3 hours, I'm so tired."

The reason why it is so fast is not only because it is fast, but also because a lot of the data inside comes from the universe USB drive and is directly imported, saving a lot of effort.

Originally, Chen Yao wanted to find the finished product of the dubbing software directly on the USB flash drive, so that he would not have to write the code by himself.

However, the USB flash drive has only unlocked the first Aries partition. This partition has no finished product. It requires more points to unlock other partitions.

In fact, after thinking about it, it is good to have the dark horse dubbing software involved in the compilation of it, and it has a stronger sense of accomplishment, and it doesn’t take much time anyway.

Now there is a dubbing software and a voice engine. Next, we will produce pronunciation roles.

...

PS: I wonder if you have used Qidian Reading’s voice reading function? You might as well listen to your feelings with your voice.

What Chen Yao is doing now is definitely much more powerful than today's voice technology.
Chapter completed!