Rana el Kaliouby: This app knows how you feel — from the look on your face

137,190 views ・ 2015-06-15

TED


請雙擊下方英文字幕播放視頻。

譯者: Regina Chu 審譯者: Marssi Draw
00:12
Our emotions influence every aspect of our lives,
0
12556
4017
我們的情緒會影響 日常生活的各個層面,
00:16
from our health and how we learn, to how we do business and make decisions,
1
16573
3576
從我們的健康到如何學習、 如何做事、做決定,
00:20
big ones and small.
2
20149
1773
無論事情大小都受此影響。
00:22
Our emotions also influence how we connect with one another.
3
22672
3490
我們的情緒也會影響 我們如何與他人交流。
00:27
We've evolved to live in a world like this,
4
27132
3976
我們已經進化到生活在 一個像這樣的世界,
00:31
but instead, we're living more and more of our lives like this --
5
31108
4319
然而我們的生活卻愈來愈像這樣──
00:35
this is the text message from my daughter last night --
6
35427
3134
這是我女兒昨晚傳來的簡訊──
00:38
in a world that's devoid of emotion.
7
38561
2740
一個缺乏情感的世界。
00:41
So I'm on a mission to change that.
8
41301
1951
所以我帶著使命要改變這種狀況。
00:43
I want to bring emotions back into our digital experiences.
9
43252
4091
我想將情感重新注入數位體驗中。
00:48
I started on this path 15 years ago.
10
48223
3077
我在 15 年前走上這條路。
00:51
I was a computer scientist in Egypt,
11
51300
2066
當時我在埃及是電腦科學家,
00:53
and I had just gotten accepted to a Ph.D. program at Cambridge University.
12
53366
4505
而且我才拿到劍橋大學 博士班的入學許可。
00:57
So I did something quite unusual
13
57871
2113
所以我做了一件 對身為年輕新婚的埃及回教婦女來說
00:59
for a young newlywed Muslim Egyptian wife:
14
59984
4225
相當不尋常的事:
01:05
With the support of my husband, who had to stay in Egypt,
15
65599
2999
在我先生的支持下, 他留在埃及,
01:08
I packed my bags and I moved to England.
16
68598
3018
我整理行囊搬到英格蘭。
01:11
At Cambridge, thousands of miles away from home,
17
71616
3228
在劍橋,離家千里遠的地方,
01:14
I realized I was spending more hours with my laptop
18
74844
3413
我發現我與筆電相處的時間,
01:18
than I did with any other human.
19
78257
2229
遠超過與人交流的時間。
01:20
Yet despite this intimacy, my laptop had absolutely no idea how I was feeling.
20
80486
4853
儘管與筆電相處如此親密, 它卻完全不了解我的感受,
01:25
It had no idea if I was happy,
21
85339
3211
它不知道我是否開心,
01:28
having a bad day, or stressed, confused,
22
88550
2988
今天順不順,是否緊張或困惑,
01:31
and so that got frustrating.
23
91538
2922
所以那令我沮喪。
01:35
Even worse, as I communicated online with my family back home,
24
95600
5231
更糟的是,在我上線 與遠方的家人聯絡時,
01:41
I felt that all my emotions disappeared in cyberspace.
25
101421
3282
我覺得我的情感 在這虛擬空間裡消失無蹤。
01:44
I was homesick, I was lonely, and on some days I was actually crying,
26
104703
5155
我好想家,我好孤單, 有些日子我真的哭了,
01:49
but all I had to communicate these emotions was this.
27
109858
4928
但我所能傳達的只有這個。
01:54
(Laughter)
28
114786
2020
(笑聲)
01:56
Today's technology has lots of I.Q., but no E.Q.;
29
116806
4974
今天的科技有很多智商, 卻沒有情緒智商;
02:01
lots of cognitive intelligence, but no emotional intelligence.
30
121780
3176
有很多認知智商, 卻沒有情緒智商。
02:04
So that got me thinking,
31
124956
2197
所以這讓我思考,
02:07
what if our technology could sense our emotions?
32
127153
3624
如果我們的科技可以 感受我們的情緒會怎樣?
02:10
What if our devices could sense how we felt and reacted accordingly,
33
130777
4076
如果我們的電子裝置可以 感受我們的感覺並做出相對回應,
02:14
just the way an emotionally intelligent friend would?
34
134853
3013
就像一位高情商的朋友一樣, 會是怎樣?
02:18
Those questions led me and my team
35
138666
3564
這些問題讓我及我的團隊
02:22
to create technologies that can read and respond to our emotions,
36
142230
4377
創造出可以讀懂情緒 並做出回應的科技,
02:26
and our starting point was the human face.
37
146607
3090
我們的起始點是人的臉。
02:30
So our human face happens to be one of the most powerful channels
38
150577
3173
人類的臉恰好就是有力的管道,
02:33
that we all use to communicate social and emotional states,
39
153750
4016
能用來傳遞社交及情緒狀態,
02:37
everything from enjoyment, surprise,
40
157766
3010
從愉快、驚訝,
02:40
empathy and curiosity.
41
160776
4203
到同情、好奇都可以。
02:44
In emotion science, we call each facial muscle movement an action unit.
42
164979
4928
情緒科學中,我們稱每一種 顏面肌肉運動為一個動作單位。
02:49
So for example, action unit 12,
43
169907
2925
舉例來說,動作單位 12,
02:52
it's not a Hollywood blockbuster,
44
172832
2038
這可不是好萊塢的動作巨片,
02:54
it is actually a lip corner pull, which is the main component of a smile.
45
174870
3442
這其實是拉嘴角, 這是微笑的主要部分。
02:58
Try it everybody. Let's get some smiles going on.
46
178312
2988
大家都試一下吧! 讓會場有點笑容。
03:01
Another example is action unit 4. It's the brow furrow.
47
181300
2654
另一個例子是動作單位 4。 這是蹙額。
03:03
It's when you draw your eyebrows together
48
183954
2238
就是你把眉頭皺在一起
03:06
and you create all these textures and wrinkles.
49
186192
2267
所產生的紋理和皺紋。
03:08
We don't like them, but it's a strong indicator of a negative emotion.
50
188459
4295
我們都不喜歡皺紋, 但那是負面情緒的重要指標。
03:12
So we have about 45 of these action units,
51
192754
2206
我們有約 45 種動作單位,
03:14
and they combine to express hundreds of emotions.
52
194960
3390
排列組合後可以表現出數百種情緒。
03:18
Teaching a computer to read these facial emotions is hard,
53
198350
3901
要教電腦讀懂這些顏面表情很難,
03:22
because these action units, they can be fast, they're subtle,
54
202251
2972
因為這些動作單位很快、很細微,
03:25
and they combine in many different ways.
55
205223
2554
而且還有各種不同的組合法。
03:27
So take, for example, the smile and the smirk.
56
207777
3738
所以再舉個例子,微笑和假笑。
03:31
They look somewhat similar, but they mean very different things.
57
211515
3753
兩者看起來有點像, 但是意義大不相同。
03:35
(Laughter)
58
215268
1718
(笑聲)
03:36
So the smile is positive,
59
216986
3004
微笑是正面的,
03:39
a smirk is often negative.
60
219990
1270
假笑往往是負面的。
03:41
Sometimes a smirk can make you become famous.
61
221260
3876
有時候一個假笑可以讓你成名。
03:45
But seriously, it's important for a computer to be able
62
225136
2824
但是說真的,要讓電腦能夠
03:47
to tell the difference between the two expressions.
63
227960
2855
辨認出這兩種表情的不同很重要。
03:50
So how do we do that?
64
230815
1812
所以我們怎麼做呢?
03:52
We give our algorithms
65
232627
1787
我們給我們的演算法
03:54
tens of thousands of examples of people we know to be smiling,
66
234414
4110
成千上萬筆我們知道在微笑的例子,
03:58
from different ethnicities, ages, genders,
67
238524
3065
各式人種、年齡、性別都有,
04:01
and we do the same for smirks.
68
241589
2811
假笑也如法泡製。
04:04
And then, using deep learning,
69
244400
1554
然後,機器用深度學習法,
04:05
the algorithm looks for all these textures and wrinkles
70
245954
2856
讓演算法找出臉上 所有的紋理、皺紋,
04:08
and shape changes on our face,
71
248810
2580
及臉型的改變,
04:11
and basically learns that all smiles have common characteristics,
72
251390
3202
基本上學得所有的微笑 都有共同的特點,
04:14
all smirks have subtly different characteristics.
73
254592
3181
所有的假笑也有 稍稍不同的特點,
04:17
And the next time it sees a new face,
74
257773
2368
所以下一次電腦看到新的面孔,
04:20
it essentially learns that
75
260141
2299
它基本上會得知
04:22
this face has the same characteristics of a smile,
76
262440
3033
這張臉與微笑有相同的特點,
04:25
and it says, "Aha, I recognize this. This is a smile expression."
77
265473
4278
然後它會說,「啊哈! 我認得這個,這是微笑的表情。」
04:30
So the best way to demonstrate how this technology works
78
270381
2800
要展示怎麼用 這項科技的最佳方法,
04:33
is to try a live demo,
79
273181
2136
就是來一個現場示範,
04:35
so I need a volunteer, preferably somebody with a face.
80
275317
3913
所以我需要一名志願者, 最好是有臉的。
04:39
(Laughter)
81
279230
2334
(笑聲)
04:41
Cloe's going to be our volunteer today.
82
281564
2771
我們今天的志願者是克蘿伊。
04:45
So over the past five years, we've moved from being a research project at MIT
83
285325
4458
過去五年,我們從 麻省理工的一項研究計畫
04:49
to a company,
84
289783
1156
發展成一家公司,
04:50
where my team has worked really hard to make this technology work,
85
290939
3192
我的團隊很努力 讓這項科技能快速傳播,
04:54
as we like to say, in the wild.
86
294131
2409
好像我們常說的,(病毒)擴散中。
04:56
And we've also shrunk it so that the core emotion engine
87
296540
2670
我們也把它縮小, 讓核心情緒引擎能用在
04:59
works on any mobile device with a camera, like this iPad.
88
299210
3320
任何有照相機的行動裝置上, 像是這台 iPad。
05:02
So let's give this a try.
89
302530
2786
現在來試一下。
05:06
As you can see, the algorithm has essentially found Cloe's face,
90
306756
3924
正如你們所見,基本上 演算法已經找到了克蘿伊的臉,
05:10
so it's this white bounding box,
91
310680
1692
就是這個白色的框框,
05:12
and it's tracking the main feature points on her face,
92
312372
2571
它正在找她臉上的 幾個主要特徵點,
05:14
so her eyebrows, her eyes, her mouth and her nose.
93
314943
2856
像是她的眉毛、 眼睛、嘴巴和鼻子。
05:17
The question is, can it recognize her expression?
94
317799
2987
問題是,它能辨識她的表情嗎?
05:20
So we're going to test the machine.
95
320786
1671
我們來考一下機器。
05:22
So first of all, give me your poker face. Yep, awesome. (Laughter)
96
322457
4186
首先,來一張撲克臉。 對,好極了!(笑聲)
05:26
And then as she smiles, this is a genuine smile, it's great.
97
326643
2813
然後她微笑的時後, 這是真誠的微笑,很棒,
05:29
So you can see the green bar go up as she smiles.
98
329456
2300
你們可以看到她微笑的時候, 綠色的信號格增加。
05:31
Now that was a big smile.
99
331756
1222
那可是個好大的微笑。
05:32
Can you try a subtle smile to see if the computer can recognize?
100
332978
3043
你可以試一下淺淺的微笑嗎? 看看電腦能不能辨識?
05:36
It does recognize subtle smiles as well.
101
336021
2331
它的確也能辨識淺淺的微笑。
05:38
We've worked really hard to make that happen.
102
338352
2125
我們真的很努力要做到這一點。
05:40
And then eyebrow raised, indicator of surprise.
103
340477
2962
然後抬眉毛,表示驚訝。
05:43
Brow furrow, which is an indicator of confusion.
104
343439
4249
蹙額,表示困惑。
05:47
Frown. Yes, perfect.
105
347688
4007
皺眉,很好,很完美。
05:51
So these are all the different action units. There's many more of them.
106
351695
3493
這些就是不同的動作單位。 還有更多。
05:55
This is just a slimmed-down demo.
107
355188
2032
這只是瘦身版示範。
05:57
But we call each reading an emotion data point,
108
357220
3148
我們稱每一個讀取 為一個情緒資料點,
06:00
and then they can fire together to portray different emotions.
109
360368
2969
然後它們一起發動 就能描繪出不同的情緒。
06:03
So on the right side of the demo -- look like you're happy.
110
363337
4653
右邊的這張示範── 表現你很開心。
06:07
So that's joy. Joy fires up.
111
367990
1454
所以那是高興。高興出現了。
06:09
And then give me a disgust face.
112
369444
1927
然後給我一張噁心的臉。
06:11
Try to remember what it was like when Zayn left One Direction.
113
371371
4272
試著回想贊恩退出 男團一世代的那種感覺。
06:15
(Laughter)
114
375643
1510
(笑聲)
06:17
Yeah, wrinkle your nose. Awesome.
115
377153
4342
沒錯,皺鼻子。太棒了!
06:21
And the valence is actually quite negative, so you must have been a big fan.
116
381495
3731
效價呈現高負值, 所以你一定是大粉絲。
06:25
So valence is how positive or negative an experience is,
117
385226
2700
效價指的是感受的好壞程度,
06:27
and engagement is how expressive she is as well.
118
387926
2786
而投入程度指的是 她的表情有多大。
06:30
So imagine if Cloe had access to this real-time emotion stream,
119
390712
3414
想像一下如果克羅伊 能使用這套即時情緒串流,
06:34
and she could share it with anybody she wanted to.
120
394126
2809
而且她還可以跟任何人分享。
06:36
Thank you.
121
396935
2923
謝謝妳!
06:39
(Applause)
122
399858
4621
(掌聲)
06:45
So, so far, we have amassed 12 billion of these emotion data points.
123
405749
5270
到目前為止我們已經 累積了 120 億筆情緒數據點。
06:51
It's the largest emotion database in the world.
124
411019
2611
這是世界上最大的情緒資料庫。
06:53
We've collected it from 2.9 million face videos,
125
413630
2963
我們從 290 萬筆臉孔短片 收集資料,
06:56
people who have agreed to share their emotions with us,
126
416593
2600
由同意與我們分享他們情緒的人提供,
06:59
and from 75 countries around the world.
127
419193
3205
來源遍及全球 75 個國家。
07:02
It's growing every day.
128
422398
1715
資料每天都在增加。
07:04
It blows my mind away
129
424603
2067
這真令我驚異萬分,
07:06
that we can now quantify something as personal as our emotions,
130
426670
3195
我們能量化像情緒 這麼個人的東西,
07:09
and we can do it at this scale.
131
429865
2235
還能做到這個地步。
07:12
So what have we learned to date?
132
432100
2177
所以至今我們學到什麼?
07:15
Gender.
133
435057
2331
性別。
07:17
Our data confirms something that you might suspect.
134
437388
3646
我們的數據證實了一些 你們大概已經料到的事。
07:21
Women are more expressive than men.
135
441034
1857
女人的表情比男人的更豐富。
07:22
Not only do they smile more, their smiles last longer,
136
442891
2683
她們不但更常微笑, 微笑的時間還更久,
07:25
and we can now really quantify what it is that men and women
137
445574
2904
而且我們現在真的能量化
造成男女不同反應的東西。
07:28
respond to differently.
138
448478
2136
07:30
Let's do culture: So in the United States,
139
450614
2290
來看文化:在美國,
07:32
women are 40 percent more expressive than men,
140
452904
3204
女性比男性多 40% 更願意表達情感,
07:36
but curiously, we don't see any difference in the U.K. between men and women.
141
456108
3645
但奇怪的是, 在英國看不到這樣的差距。
07:39
(Laughter)
142
459753
2506
(笑聲)
07:43
Age: People who are 50 years and older
143
463296
4027
再看年齡:50 歲以上的人
07:47
are 25 percent more emotive than younger people.
144
467323
3436
比年輕人多 25% 更願意表現情感。
07:51
Women in their 20s smile a lot more than men the same age,
145
471899
3852
20 多歲的女性 比同年齡的男性更常微笑,
07:55
perhaps a necessity for dating.
146
475751
3839
大概是因為這是約會必殺技。
07:59
But perhaps what surprised us the most about this data
147
479590
2617
但是這筆數據最讓我們訝異的,
08:02
is that we happen to be expressive all the time,
148
482207
3203
大概是我們隨時都有表情,
08:05
even when we are sitting in front of our devices alone,
149
485410
2833
即使我們獨自坐在裝置前也是如此,
08:08
and it's not just when we're watching cat videos on Facebook.
150
488243
3274
而且不只是在我們看 臉書上貓短片的的時候。
08:12
We are expressive when we're emailing, texting, shopping online,
151
492217
3010
我們在寫信、傳簡訊、網購,
08:15
or even doing our taxes.
152
495227
2300
甚至在報稅時都表情豐富。
08:17
Where is this data used today?
153
497527
2392
今天這筆數據用在哪裡呢?
08:19
In understanding how we engage with media,
154
499919
2763
用在瞭解我們如何與媒體互動,
08:22
so understanding virality and voting behavior;
155
502682
2484
所以能瞭解影片爆紅及投票行為,
08:25
and also empowering or emotion-enabling technology,
156
505166
2740
也用在情緒辨識科技,
08:27
and I want to share some examples that are especially close to my heart.
157
507906
4621
我想分享幾個 讓我特別感動的例子。
08:33
Emotion-enabled wearable glasses can help individuals
158
513197
3068
情緒辨識眼鏡能幫助
08:36
who are visually impaired read the faces of others,
159
516265
3228
視障者讀取別人臉上的表情,
08:39
and it can help individuals on the autism spectrum interpret emotion,
160
519493
4187
也能幫助各種程度的 自閉症患者解讀情緒,
08:43
something that they really struggle with.
161
523680
2778
這是他們的最大難題。
08:47
In education, imagine if your learning apps
162
527918
2859
在教育上,想像一下 如果你的學習應用程式
08:50
sense that you're confused and slow down,
163
530777
2810
感受到你的困惑並放慢速度,
08:53
or that you're bored, so it's sped up,
164
533587
1857
或是知道你覺得無聊了 所以加快速度,
08:55
just like a great teacher would in a classroom.
165
535444
2969
就像一位好老師 在課堂上做的一樣。
08:59
What if your wristwatch tracked your mood,
166
539043
2601
如果你的手錶能追蹤你的心情,
09:01
or your car sensed that you're tired,
167
541644
2693
或是你的車能感受到 你現在很疲倦,
09:04
or perhaps your fridge knows that you're stressed,
168
544337
2548
或是你的冰箱能知道 你現在壓力很大,
09:06
so it auto-locks to prevent you from binge eating. (Laughter)
169
546885
6066
所以它會自動鎖住, 你就不能拿東西來吃。(笑聲)
我會喜歡那個,真的。
09:12
I would like that, yeah.
170
552951
2717
09:15
What if, when I was in Cambridge,
171
555668
1927
當我在劍橋的時候,
09:17
I had access to my real-time emotion stream,
172
557595
2313
如果我能用這套 即時情緒串流工具,
09:19
and I could share that with my family back home in a very natural way,
173
559908
3529
我就能用非常自然的方法 與遠在家鄉的家人分享,
09:23
just like I would've if we were all in the same room together?
174
563437
3971
就好像我們都在 同一間房間一樣,那有多好?
09:27
I think five years down the line,
175
567408
3142
我想五年後,
09:30
all our devices are going to have an emotion chip,
176
570550
2337
我們所有的裝置 都會有一個情緒晶片,
09:32
and we won't remember what it was like when we couldn't just frown at our device
177
572887
4064
我們就會忘記當年 裝置還不會回應我們皺眉的時候說出:
09:36
and our device would say, "Hmm, you didn't like that, did you?"
178
576951
4249
「嗯,你不喜歡這個,是吧?」 是什麼樣子。
09:41
Our biggest challenge is that there are so many applications of this technology,
179
581200
3761
我們最大的挑戰是 這種科技有許多應用程式,
09:44
my team and I realize that we can't build them all ourselves,
180
584961
2903
我和我的團隊瞭解 我們不可能只靠自己發展全部,
09:47
so we've made this technology available so that other developers
181
587864
3496
所以我們開放這項科技 讓其他開發者
09:51
can get building and get creative.
182
591360
2114
能繼續開發並激發創意。
09:53
We recognize that there are potential risks
183
593474
4086
我們知道會有潛在風險,
09:57
and potential for abuse,
184
597560
2067
也可能遭到濫用,
09:59
but personally, having spent many years doing this,
185
599627
2949
但是個人認為, 在花了這麼多年做這個之後,
10:02
I believe that the benefits to humanity
186
602576
2972
我相信這對人類的益處,
10:05
from having emotionally intelligent technology
187
605548
2275
就是開發情緒智能科技的益處,
10:07
far outweigh the potential for misuse.
188
607823
3576
遠超過誤用的潛在危險。
10:11
And I invite you all to be part of the conversation.
189
611399
2531
我請大家口耳相傳。
10:13
The more people who know about this technology,
190
613930
2554
愈多人知道這項科技,
10:16
the more we can all have a voice in how it's being used.
191
616484
3177
我們就愈能發聲說明 這該如何使用。
10:21
So as more and more of our lives become digital,
192
621081
4574
隨著我們的生活愈來愈數位化,
10:25
we are fighting a losing battle trying to curb our usage of devices
193
625655
3498
試圖以遏止使用裝置來重拾情緒
10:29
in order to reclaim our emotions.
194
629153
2229
是一場必敗的仗。
10:32
So what I'm trying to do instead is to bring emotions into our technology
195
632622
3914
與其如此, 我寧可把情感帶進科技,
10:36
and make our technologies more responsive.
196
636536
2229
讓我們的科技更有回應。
10:38
So I want those devices that have separated us
197
638765
2670
所以我想用這些 原本使我們疏遠的裝置,
10:41
to bring us back together.
198
641435
2462
讓我們重新結合在一起。
10:43
And by humanizing technology, we have this golden opportunity
199
643897
4588
藉著把科技人性化, 我們擁有這個黃金時機
10:48
to reimagine how we connect with machines,
200
648485
3297
來重新想像我們如何 與機器連結,
10:51
and therefore, how we, as human beings,
201
651782
4481
進而想像我們身為人類
10:56
connect with one another.
202
656263
1904
如何能重新連結彼此。
10:58
Thank you.
203
658167
2160
謝謝。
11:00
(Applause)
204
660327
3313
(掌聲)
關於本網站

本網站將向您介紹對學習英語有用的 YouTube 視頻。 您將看到來自世界各地的一流教師教授的英語課程。 雙擊每個視頻頁面上顯示的英文字幕,從那裡播放視頻。 字幕與視頻播放同步滾動。 如果您有任何意見或要求,請使用此聯繫表與我們聯繫。

https://forms.gle/WvT1wiN1qDtmnspy7