Introduction

Sometimes it can be difficult to tell if someone is really smiling or the smirk on their face is fake. But now there are?computers that are able tell real smiles from fake ones better than humans can. How do they work and what are the benefits? It's something Neil and Sam are discussing in 6 Minute English - as well as teaching you some useful vocabulary that will hopefully bring a smile to your face.

This week's question

The expressions we can make with our face are controlled by muscles. How many muscles do we have in our face? Is it:

A: 26

B: 43

C: 62

Listen to the programme to find out the answer.

Vocabulary

facial

adjective to do with the face

to infer

to come to a decision about something using the information you have, which may not be complete

in real time

at the same time as, without delay

to induce

to cause something to happen

genuine

real, not fake

to figure out

to calculate, to work out

Transcript?

Note: This is not a word for word transcript????

Neil

Hello. This is 6 Minute English, I'm Neil.

Sam

And I'm Sam.

Neil

It’s good to see you again, Sam.

Sam

Really?

Neil

Yes, of course, can’t you tell by the way I’m smiling?

Sam

Ah well, I find it difficult to tell if someone is really smiling or if it’s a fake smile.

Neil

Well, that’s a coincidence because today’s programme is all about how computers may be able tell real smiles from fake smiles better than humans can. Before we get in to that though, a question. The expressions we can make with our face are controlled by muscles. How many muscles do we have in our face? Is it:

A: 26

B: 43

C: 62

What do you think, Sam?

Sam

No idea! But a lot, I’d guess, so I’m going with 62.

Neil

OK. Well, we’ll see if you’ll be smiling or crying later in the programme. Hassan Ugail is a professor of visual computing at the University of Bradford. He’s been working on getting computers to be able to recognise human emotions from the expressions on our face. Here he is speaking on the BBC Inside Science radio programme – how successful does he say they have been?

Professor Hassan Ugail

We've been working quite a lot on the human emotions, so the idea is how the facial muscle movement, which is reflected on the face, through obviously a computer through video frames and trying to understand how these muscle movements actually relate to facial expressions and then from facial expressions trying to understand the emotions or to infer the emotions. And they have been quite successful in doing that. We have software that can actually look at somebody's face in real time and then identify the series of emotions that person is expressing in real time as well.

Neil

So, have they been successful in getting computers to identify emotions?

Sam

Yes, he says they’ve been quite successful, and what’s interesting is that he says that the computers can do it in real time. This means that there’s no delay. They don’t have to stop and analyse the data, or crunch the numbers, they can do it as the person is talking.

Neil

The system uses video to analyse a person’s expressions and can then infer the emotions. To infer something means to get an understanding of something without actually being told directly. So, you look at available information and use your understanding and knowledge to work out the meaning.

Sam

It’s a bit like being a detective, isn’t it? You look at the clues and infer what happened even if you don’t have all the details.

Neil

Yes, and in this case the computer looks at how the movement of muscles in the face or facial muscles, show different emotions. Here’s Professor Ugail again.

Professor Hassan Ugail

We've been working quite a lot on the human emotions so the idea is how the facial muscle movement, which is reflected on the face, through obviously a computer through video frames and trying to understand how these muscle movements actually relate to facial expressions and then from facial expressions trying to understand the emotions or to infer the emotions. And they have been quite successful in doing that. We have software that can actually look at somebody's face in real time and then identify the series of emotions that person is expressing in real time as well.

Neil

So, how do the computers know what is a real or a fake smile? The computers have to learn that first. Here’s Professor Ugail again talking about how they do that.

Professor Hassan Ugail

We have a data set of real smiles and we have a data set of fake smiles. These real smiles are induced smiles in a lab. So, you put somebody on a chair and then show some funny movies and we expect the smiles are genuine smiles. And similarly we ask them to pretend to smile. So, these are what you'd call fake smiles. So, what we do is we throw these into the machine and then the machine figures out what are the characteristics of a real smile and what are the characteristics of a fake smile.

Neil

So, how do they get the data that the computers use to see if your smile is fake or genuine – which is another word which means real?

Sam

They induce real smiles in the lab by showing people funny films. This means that they make the smiles come naturally. They assume that the smiles while watching the funny films are genuine.

Neil

And then they ask the people to pretend to smile and the computer programme now has a database of real and fake smiles and is able to figure out which is which.

Sam

Figure out means to calculate and come to an answer

Neil

Yes, and apparently the system gets it right 90% of the time, which is much higher than we humans can. Right, well before we remind ourselves of our vocabulary, let’s get the answer to the question. How many muscles do we have in our face? Is it:

A: 26

B: 43

C: 62

Sam, are you going to be smiling? What did you say?

Sam

So I thought 62! Am I smiling, Neil?

Neil

Sadly you are not, you are using different muscles for that sort of sad look! Actually the answer is 43. Congratulations to anyone who got that right. Now our vocabulary.

Sam

Yes – facial is the adjective relating to face.

Neil

Then we had infer. This verb means to understand something even when you don’t have all the information, and you come to this understanding based on your experience and knowledge, or in the case of a computer, the programming.

Sam

And these computers work in real time, which means that there’s no delay and they can tell a fake smile from a genuine one, which means a real one, as the person is speaking.

Neil

They made people smile, or as the Professor said, they induced smiles by showing funny films.

Sam

And the computer is able to figure out or calculate whether the smile is fake or genuine.

Neil

OK, thank you, Sam. That’s all from 6 Minute English today. We look forward to your company next time and if you can’t wait you can find lots more from bbclearningenglish online, on social media and on our app. Goodbye!

Sam

Bye!

===========================================================

Hello. This is 6 Minute English, I'm Neil.

大家好，這里是六分鐘英語，我是尼爾。

And I'm Sam.

我是薩姆。

It's good to see you again, Sam.

很高興再次見到你，薩姆。

Really?

真的？

Yes, of course, can't you tell by the way I'm smiling?

是啊，當(dāng)然，從我在笑這點你還看不出來嗎？

Ah well, I find it difficult to tell if someone is really smiling or if it's a fake smile.

好吧，我發(fā)現(xiàn)很難分辨一個人是真笑還是假笑。

Well, that's a coincidence because today's programme is all about how computers may be able tell real smiles from fake smiles better than humans can.

好吧，那只是巧合，因為今天的節(jié)目是關(guān)于計算機(jī)如何比人類更好地分辨真笑和假笑。

Before we get in to that though, a question.

然而在我們開始之前有一個問題。

The expressions we can make with our face are controlled by muscles.

我們所做面部表情是由肌肉控制的。

How many muscles do we have in our face?

我們臉上有多少塊肌肉？

Is it: A: 26, B: 43, or C: 62?

是A：?26塊，?B：?43塊，還是C：?62塊？

What do you think, Sam?

你覺得呢，薩姆？

No idea!

不知道！

But a lot, I'd guess, so I'm going with 62.

但我猜有很多塊，所以我選62塊。

OK. Well, we'll see if you'll be smiling or crying later in the programme.

好的。我們稍后將在節(jié)目中看看你是答對而笑還是答錯而哭。

Hassan Ugail is a professor of visual computing at the University of Bradford.

哈山·?優(yōu)格里是布拉德福德大學(xué)的視覺計算方面的教授。

He's been working on getting computers to be able to recognise human emotions from the expressions on our face.

他一直致力于讓計算機(jī)能夠從我們的面部表情而識別人類情緒。

Here he is speaking on the BBC Inside Science radio programme?– how successful does he say they have been?

這是他在BBC廣播Inside Science節(jié)目上的講話——他說他們有多成功？

We've been working quite a lot on the human emotions, so the idea is how the facial muscle movement, which is reflected on the face, through obviously a computer through video frames,?and trying to understand how these muscle movements actually relate to facial expressions and then from facial expressions trying to understand the emotions or to infer the emotions.

我們在人類情緒方面做了很多工作，所以我們的想法是通過計算機(jī)，通過視頻幀來了解體現(xiàn)在臉上的面部肌肉運動是怎樣的，并試圖了解這些肌肉運動實際上與面部表情之間的聯(lián)系，然后根據(jù)面部表情嘗試?yán)斫馇榫w或推斷情緒。

And they have been quite successful in doing that.

大家在這方面做得很成功。

We have software that can actually look at somebody's face in real time and then identify the series of emotions that person is expressing in real time as well.

我們有軟件，它可以實時觀察人們的面部，然后識別這個人實時表達(dá)的一系列情緒。

So, have they been successful in getting computers to identify emotions?

那么他們成功地讓計算機(jī)識別情緒了嗎？

Yes, he says they've been quite successful, and what's interesting is that he says that the computers can do it in real time.

是的，他說他們已經(jīng)相當(dāng)成功了，有趣的是，他說計算機(jī)可以實時做到那些。

This means that there's no delay.

這意味著沒有延遲。

They don't have to stop and analyse the data, or crunch the numbers, they can do it as the person is talking.

他們不需要停下來分析數(shù)據(jù)，或者處理數(shù)據(jù)，他們可以在人們說著話的時候進(jìn)行分析。

The system uses video to analyse a person's expressions and can then infer the emotions.

該系統(tǒng)利用視頻分析一個人的表情，然后就能推斷出他的情緒。

To infer something means to get an understanding of something without actually being told directly.

"推斷"指的是在沒有被直接告知的情況下了解某事。

So, you look at available information and use your understanding and knowledge to work out the meaning.

所以，你根據(jù)可用信息，用你的理解和知識來弄明白。

It's a bit like being a detective, isn't it?

這有點像當(dāng)偵探，不是嗎？

You look at the clues and infer what happened even if you don't have all the details.

即使你不知道所有的細(xì)節(jié)，你也會根據(jù)線索推斷出發(fā)生了什么。

Yes, and in this case the computer looks at how the movement of muscles in the face or facial muscles, show different emotions.

是的，在這種情況下，計算機(jī)會觀察臉上肌肉運動或面部肌肉運動是如何表現(xiàn)不同情緒的。

Here's Professor Ugail again.

再聽一遍優(yōu)格里教授說的。

We've been working quite a lot on the human emotions, so the idea is how the facial muscle movement, which is reflected on the face, through obviously a computer through video frames,?and trying to understand how these muscle movements actually relate to facial expressions and then from facial expressions trying to understand the emotions or to infer the emotions.

我們在人類情緒方面做了很多工作，所以我們的想法是通過計算機(jī)，通過視頻幀來了解體現(xiàn)在臉上的面部肌肉運動是怎樣的，并試圖了解這些肌肉運動實際上與面部表情之間的聯(lián)系，然后根據(jù)面部表情嘗試?yán)斫馇榫w或推斷情緒。

And they have been quite successful in doing that.

大家在這方面做得很成功。

We have software that can actually look at somebody's face in real time and then identify the series of emotions that person is expressing in real time as well.

我們有軟件，它可以實時觀察人們的面部，然后識別這個人實時表達(dá)的一系列情緒。

So, how do the computers know what is a real or a fake smile?

那么，計算機(jī)如何知道什么是真笑，什么是假笑？

The computers have to learn that first.

計算機(jī)必須先掌握這一點。

Here's Professor Ugail again talking about how they do that.

這是優(yōu)格里教授再次談?wù)撍麄兪侨绾巫龅降摹?/span>

We have a data set of real smiles and we have a data set of fake smiles.

我們有真笑和假笑的數(shù)據(jù)集。

These real smiles are induced smiles in a lab.

這些真笑是在實驗室被誘導(dǎo)產(chǎn)生的。

So, you put somebody on a chair and then show some funny movies and we expect the smiles are genuine smiles.

所以，你讓某人坐在椅子上，然后播放一些搞笑電影，我們認(rèn)為這些微笑是真笑。

And similarly we ask them to pretend to smile. So, these are what you'd call fake smiles.

同樣我們讓他們假裝微笑。那么，這些就是你們所說的假笑。

So, what we do is we throw these into the machine and then the machine figures out what are the characteristics of a real smile and what are the characteristics of a fake smile.

所以，我們要做的就是把這些信息導(dǎo)入機(jī)器，然后機(jī)器就會找出真笑和假笑的特征。

So, how do they get the data that the computers use to see if your smile is fake or genuine – which is another word which means real?

那么，他們是如何獲取電腦用來判斷你是真笑還是假笑的數(shù)據(jù)的——這是意思為"真實的"的另一個單詞。

They induce real smiles in the lab by showing people funny films.

他們通過給人們看搞笑電影在實驗室里誘導(dǎo)產(chǎn)生真笑。

This means that they make the smiles come naturally.

這指的是他們會自然地微笑。

They assume that the smiles while watching the funny films are genuine.

他們認(rèn)為看搞笑電影時的微笑是真實的。

And then they ask the people to pretend to smile and the computer programme now has a database of real and fake smiles and is able to figure out which is which.

然后他們讓人們假裝微笑，電腦程序現(xiàn)在有了一個真笑和假笑的數(shù)據(jù)庫，它能夠分辨出哪個是真笑，哪個是假笑。

Figure out means to calculate and come to an answer.

"Figure out"的意思是計算并得出結(jié)果。

Yes, and apparently the system gets it right 90% of the time, which is much higher than we humans can.

是的，很明顯該系統(tǒng)90%的時間是正確的，這遠(yuǎn)高于我們?nèi)祟惖哪芰Α?/span>

Right, well before we remind ourselves of our vocabulary, let's get the answer to the question.

好的，在我們復(fù)習(xí)詞匯之前，讓我們揭曉問題的答案。

How many muscles do we have in our face?

我們臉上有多少塊肌肉？

Is it: A: 26, B: 43, or C: 62?

是A：?26塊，?B：?43塊，還是C：?62塊？

Sam, are you going to be smiling? What did you say?

薩姆，你是覺得自己答對了要笑出來嗎？你說是什么？

So I thought 62! Am I smiling, Neil?

我認(rèn)為是62塊！我答對了嗎，可以笑出來嗎，尼爾？

Sadly you are not, you are using different muscles for that sort of sad look!

遺憾的是，你沒有，你在用不同的肌肉做出那種悲傷的表情！

Actually the answer is 43. Congratulations to anyone who got that right.

實際上答案是43塊。恭喜所有答對的人。

Now our vocabulary.

現(xiàn)在我們的詞匯部分。

Yes – facial is the adjective relating to face.

是的，"臉部的"是和臉有關(guān)的形容詞。

Then we had infer.

然后我們學(xué)了"推斷"。

This verb means to understand something even when you don't have all the information,?and you come to this understanding based on your experience and knowledge, or in the case of a computer, the programming.

這個動詞指的是即使你沒有掌握所有信息，你也能理解一些東西，你的這種理解是基于你的經(jīng)驗和知識，或者對于計算機(jī)而言的編程。

And these computers work in real time, which means that there's no delay,?and they can tell a fake smile from a genuine one, which means a real one, as the person is speaking.

這些電腦是實時工作的，這意味著沒有延遲，它們可以在人們說著話的時候分辨假笑和真笑，那指的是真實的笑容。

They made people smile, or as the Professor said, they induced smiles by showing funny films.

他們讓人們微笑，或者如教授所說，他們通過播放搞笑電影來誘導(dǎo)人們微笑。

And the computer is able to figure out or calculate whether the smile is fake or genuine.

而計算機(jī)可以斷定出微笑是真是假。

OK, thank you, Sam. That's all from 6 Minute English today.

好的，謝謝你，薩姆。以上就是本期六分鐘英語的全部內(nèi)容。

We look forward to your company next time,?Goodbye!

我們期待你的下次參與，再見！

Bye-bye