TEDWomen 2013
Rupal Patel: Synthetic voices, as unique as fingerprints
露波‧帕特爾: 像指紋一樣獨特的智能聲音
Filmed:
Readability: 3.9
944,754 views
大部分患有語言障礙的人都使用一種電腦化的設備來溝通，但是可選擇的聲音卻不多。這也是為甚麼史蒂芬·霍金的聲音是美國口音，而很多人都用著同一個聲音，不符合他們身份的聲音。語言科學家露波‧帕特爾決定改變這一狀況。在這個演講中，她將與大家分享她為“無音人士”創造獨特聲音的過程。
Rupal Patel - Speech scientist
People relying on synthetic speech use the voice they’re given, not their own. Rupal Patel created the vocaliD project to change that. Full bio
People relying on synthetic speech use the voice they’re given, not their own. Rupal Patel created the vocaliD project to change that. Full bio
Double-click the English transcript below to play the video.
00:12
I'd like to talk today
0
719
1490
我今天想給大家介紹
00:14
about a powerful and fundamental aspect
1
2209
2927
一個對我們身份有重要影響的因素
00:17
of who we are: our voice.
2
5136
3598
那就是:聲音
00:20
Each one of us has a unique voiceprint
3
8734
2746
我們每一個人都有獨特的音印
00:23
that reflects our age, our size,
4
11480
2289
它反映了我們的年紀, 體型,
00:25
even our lifestyle and personality.
5
13769
3237
甚至我們的性格與生活習慣
00:29
In the words of the poet Longfellow,
6
17006
2142
以詩人亨利·沃茲沃思·朗費羅的話說:
00:31
"the human voice is the organ of the soul."
7
19148
3870
"人類的聲音就是靈魂的器官."
00:35
As a speech scientist, I'm fascinated
8
23018
2747
做為一個語言科學家, 我對聲音產生的過程
00:37
by how the voice is produced,
9
25765
1829
有著濃厚的興趣,
00:39
and I have an idea for how it can be engineered.
10
27594
3658
我對如何來設計與建造聲音
有一個新的看法
有一個新的看法
00:43
That's what I'd like to share with you.
11
31252
2210
我想和大家分享的這個看法
00:45
I'm going to start by playing you a sample
12
33462
1814
先給大家放一個實例
00:47
of a voice that you may recognize.
13
35276
1871
你們也許認得這個聲音
00:49
(Recording) Stephen Hawking: "I would have thought
14
37147
1304
(錄音) 史蒂芬‧霍金:"我以為我說的話
00:50
it was fairly obvious what I meant."
15
38451
2749
還是比較清楚的"
00:53
Rupal Patel: That was the voice
16
41200
1280
這個錄音裡的聲音
00:54
of Professor Stephen Hawking.
17
42480
2086
是來自史蒂芬‧霍金教授
00:56
What you may not know is that same voice
18
44566
3849
但是你也許不知道同一個聲音
01:00
may also be used by this little girl
19
48415
2478
也可能被這個小女孩使用
01:02
who is unable to speak
20
50893
1697
她因為神經的問題
01:04
because of a neurological condition.
21
52590
2597
而無法說話
01:07
In fact, all of these individuals
22
55187
2068
事實上, 所有這些人
01:09
may be using the same voice,
23
57255
2012
都可能用著同一個聲音,
01:11
and that's because there's
only a few options available.
only a few options available.
24
59267
3557
因為目前可用的聲音只有幾個
01:14
In the U.S. alone, there are 2.5 million Americans
25
62824
4317
僅在美國就有250萬人
01:19
who are unable to speak,
26
67141
1610
無法通過語言溝通,
01:20
and many of whom use computerized devices
27
68751
2622
他們大多數
01:23
to communicate.
28
71373
1522
使用電子設備來溝通
01:24
Now that's millions of people worldwide
29
72895
3479
這意味著全世界有數百萬的人
01:28
who are using generic voices,
30
76374
1652
都用著同樣的聲音,
01:30
including Professor Hawking,
31
78026
1446
其中包括了霍金教授,
01:31
who uses an American-accented voice.
32
79472
4833
他用的是帶有美式口音的聲音
01:36
This lack of individuation of the synthetic voice
33
84305
3328
這種人工聲音缺少的個體性
01:39
really hit home
34
87633
1416
讓我非常的驚訝,
01:41
when I was at an assistive technology conference
35
89049
2472
當我幾年前
01:43
a few years ago,
36
91521
1850
在一個輔具科技會議上,
01:45
and I recall walking into an exhibit hall
37
93371
3604
我記得走進一個展覽廳
01:48
and seeing a little girl and a grown man
38
96975
3044
看見一個小女孩和一個成年男子
01:52
having a conversation using their devices,
39
100019
2916
通過他們的設備談話,
01:54
different devices, but the same voice.
40
102935
4284
雖然設備不同, 但聲音卻是一樣的
01:59
And I looked around and I saw this happening
41
107219
1909
我望了望四周,發現
02:01
all around me, literally hundreds of individuals
42
109128
4190
周圍有幾百個人
02:05
using a handful of voices,
43
113318
2738
使用的聲音却只有幾種
02:08
voices that didn't fit their bodies
44
116056
3091
都不符合他們的身體
02:11
or their personalities.
45
119147
2082
或是性格.
02:13
We wouldn't dream of fitting a little girl
46
121229
2727
我們不會考慮給一個小女孩裝上
02:15
with the prosthetic limb of a grown man.
47
123956
3396
一個成年男子的假肢
02:19
So why then the same prosthetic voice?
48
127352
3304
那為甚麼要給她一個
不屬於自己的聲音呢?
不屬於自己的聲音呢?
02:22
It really struck me,
49
130656
1291
我因為感觸很深,
02:23
and I wanted to do something about this.
50
131947
3151
所以決定對此做些甚麼
02:27
I'm going to play you now a sample
51
135098
1953
接下來我要播放的例子
02:29
of someone who has, two people actually,
52
137051
3288
是兩個人,
02:32
who have severe speech disorders.
53
140339
1768
他們都有嚴重的語言障礙
02:34
I want you to take a listen to how they sound.
54
142107
3230
我希望大家聽聽看他們的聲音
02:37
They're saying the same utterance.
55
145337
2357
二人說的是一樣的話
02:39
(First voice)
56
147694
2432
（聲音一）
02:42
(Second voice)
57
150126
3617
（聲音二）
02:45
You probably didn't understand what they said,
58
153743
2412
你們也許沒聽懂他們的話,
02:48
but I hope that you heard
59
156155
1854
但我希望你們注意到了
02:50
their unique vocal identities.
60
158009
4283
他們聲音中的獨特性
02:54
So what I wanted to do next is,
61
162292
2813
我接下來要做的是,
02:57
I wanted to find out how we could harness
62
165105
2384
找到一個方法來
02:59
these residual vocal abilities
63
167489
1821
利用這些剩餘的聲音特性
03:01
and build a technology
64
169310
2016
來發明一套科技
03:03
that could be customized for them,
65
171326
2143
專為他們設計
03:05
voices that could be customized for them.
66
173469
2429
將他們的聲音個性化,
03:07
So I reached out to my collaborator, Tim Bunnell.
67
175898
2685
我找到了我的合作人, 蒂姆·布涅爾
03:10
Dr. Bunnell is an expert in speech synthesis,
68
178583
3063
布涅爾博士是智能語音方面的專家,
03:13
and what he'd been doing is building
69
181646
2033
他一直都在為
03:15
personalized voices for people
70
183679
1881
他人設計個性化的語音
03:17
by putting together
71
185560
2097
方法是通過收集
03:19
pre-recorded samples of their voice
72
187657
2150
這些人之前的聲音錄音
03:21
and reconstructing a voice for them.
73
189807
2879
然後再為他們重建一種聲音
03:24
These are people who had lost their voice
74
192686
1712
但是布涅爾博士的這些研究對象
03:26
later in life.
75
194398
1911
遇到的問題是後天性語言障礙
03:28
We didn't have the luxury
76
196309
1394
我們這次的研究沒有這個福利
03:29
of pre-recorded samples of speech
77
197703
1774
對這些先天帶有語言障礙的人
03:31
for those born with speech disorder.
78
199477
2292
我們沒有事先錄製好的聲音樣品
03:33
But I thought, there had to be a way
79
201769
2537
但是我想了想, 一定有一個方法
03:36
to reverse engineer a voice
80
204306
1944
可以從僅有的所剩中
03:38
from whatever little is left over.
81
206250
2291
將聲音逆向製作出來
03:40
So we decided to do exactly that.
82
208541
2714
所以我們決定就這樣做
03:43
We set out with a little bit of funding
from the National Science Foundation,
from the National Science Foundation,
83
211255
3403
我們從國家科學基金會獲得了一些資金,
03:46
to create custom-crafted voices that captured
84
214658
3565
用以建造一套可以抓住他們
03:50
their unique vocal identities.
85
218223
1536
聲音特性的個體化語音
03:51
We call this project VocaliD, or vocal I.D.,
86
219759
3203
我們將該專案稱作VocaliD, 或是vocal I.D.,
03:54
for vocal identity.
87
222962
2033
作為語音身份(Vocal Identity)的簡寫
03:56
Now before I get into the details of how
88
224995
2674
在我向大家播放
03:59
the voice is made and let you listen to it,
89
227669
2048
和介紹如何製作這個聲音之前,
04:01
I need to give you a real quick
speech science lesson. Okay?
speech science lesson. Okay?
90
229717
3350
我需要先給大家上一堂
語言科學課, 好嗎?
語言科學課, 好嗎?
04:05
So first, we know that the voice is changing
91
233067
3159
首先,我們需要了解聲音
04:08
dramatically over the course of development.
92
236226
2854
在成長的過程中會發生巨大的變化
04:11
Children sound different from teens
93
239080
2090
兒童和青少年聽起來會不同
04:13
who sound different from adults.
94
241170
1463
而青少年和成年人之間也是
04:14
We've all experienced this.
95
242633
2642
我們都曾經歷過這些語言變化階段
04:17
Fact number two is that speech
96
245275
3363
事實二，是語言的產生
04:20
is a combination of the source,
97
248638
2553
是由多個來源組成,
04:23
which is the vibrations generated by your voice box,
98
251191
3479
其中包括了你喉頭產生的顫動,
04:26
which are then pushed through
99
254670
1939
這種顫動接著
04:28
the rest of the vocal tract.
100
256609
2437
會貫穿整個聲腔
04:31
These are the chambers of your head and neck
101
259046
2484
圖像顯示的是頭和脖子的內部
04:33
that vibrate,
102
261530
1239
它們會顫動,
04:34
and they actually filter that source sound
103
262769
2110
其實它們是將來源聲音過濾掉
04:36
to produce consonants and vowels.
104
264879
2537
來產生子音和母音
04:39
So the combination of source and filter
105
267416
3860
所以聲音的來源和過濾過程加在一起
04:43
is how we produce speech.
106
271276
2630
就是我們產生聲音的方法
04:45
And that happens in one individual.
107
273906
3026
這是一個人身上發生的過程
04:48
Now I told you earlier that I'd spent
108
276932
2626
我之前告訴過大家
04:51
a good part of my career
109
279558
2025
我職業生涯的大部分時間
04:53
understanding and studying
110
281583
2453
都用來研究和學習
04:56
the source characteristics of people
111
284036
1958
有嚴重語音障礙人士的
04:57
with severe speech disorder,
112
285994
2301
聲音源的特徵,
05:00
and what I've found
113
288295
1465
我發現
05:01
is that even though their filters were impaired,
114
289760
3366
雖然他們的過濾器官已遭到損壞,
05:05
they were able to modulate their source:
115
293126
2961
他們可以調製自己的聲音來源:
05:08
the pitch, the loudness, the tempo of their voice.
116
296087
3262
包括高低度, 大小, 以及速度
05:11
These are called prosody, and
I've been documenting for years
I've been documenting for years
117
299349
3368
這些被稱之為音律,
05:14
that the prosodic abilities of these individuals
118
302717
2277
我用了多年的時間
來紀錄這些人是如何
來紀錄這些人是如何
05:16
are preserved.
119
304994
1575
維持自己音律的能力
05:18
So when I realized that those same cues
120
306569
4087
當我認識到同樣的線索
05:22
are also important for speaker identity,
121
310656
2769
對說話人的身份同樣重要的時候,
05:25
I had this idea.
122
313425
2015
我有了一個想法
05:27
Why don't we take the source
123
315440
2516
為什麼我們不找一個
聲音是我們所需要的人,
聲音是我們所需要的人,
05:29
from the person we want the voice to sound like,
124
317956
2213
從他那採集聲音源
05:32
because it's preserved,
125
320169
1463
因為它已被保留,
05:33
and borrow the filter
126
321632
2135
然後再找一個有著相似年紀和體型的人
05:35
from someone about the same age and size,
127
323767
3229
從他那借用過濾器,
05:39
because they can articulate speech,
128
327011
2407
因為他們能清晰地說話,
05:41
and then mix them?
129
329418
1791
然後將二者混合?
05:43
Because when we mix them,
130
331209
1787
因為當我們將它們混合的時候,
05:44
we can get a voice that's as clear
131
332996
1698
我們得到的聲音將會和
05:46
as our surrogate talker --
132
334694
1754
那個代替說話者一樣清楚
05:48
that's the person we borrowed the filter from—
133
336448
2595
代替說話者就是我們借用過濾器的人
05:51
and is similar in identity to our target talker.
134
339043
4649
而產生的語音和我們
目標說話者有相似的辨認度
目標說話者有相似的辨認度
05:55
It's that simple.
135
343692
1427
就這麼簡單
05:57
That's the science behind what we're doing.
136
345119
2934
這就我們該項研究的科學性
06:00
So once you have that in mind,
137
348053
3533
有了這個想法以後,
06:03
how do you go about building this voice?
138
351586
2258
應該怎麼來製造這個聲音呢?
06:05
Well, you have to find someone
139
353844
1480
首先,你必須找一個
06:07
who is willing to be a surrogate.
140
355324
2400
願意當這個代替者的人
06:09
It's not such an ominous thing.
141
357724
2264
這個任務也不是太糟糕
06:11
Being a surrogate donor
142
359988
1523
當一個聲音捐贈者
06:13
only requires you to say a few hundred
143
361511
2788
只要求你閱讀幾百
06:16
to a few thousand utterances.
144
364299
2242
到幾千句話.
06:18
The process goes something like this.
145
366541
2003
以下是過程
06:20
(Video) Voice: Things happen in pairs.
146
368544
2190
(錄影)聲音: 事情成雙成對地發生
06:22
I love to sleep.
147
370734
1925
我愛睡覺
06:24
The sky is blue without clouds.
148
372659
3882
天空藍色無雲
06:28
RP: Now she's going to go on like this
149
376541
2002
演講者: 她接下來的3-4個小時
06:30
for about three to four hours,
150
378543
1919
都會繼續閱讀,
06:32
and the idea is not for her to say everything
151
380462
3005
目的是不要讓她說
06:35
that the target is going to want to say,
152
383467
2045
所有目標說話者要說的話
06:37
but the idea is to cover all the different combinations
153
385512
3395
真正的目的是要概擴所有
06:40
of the sounds that occur in the language.
154
388907
3271
在語言中可能發生的組合
06:44
The more speech you have,
155
392178
1638
你說的話越多,
06:45
the better sounding voice you're going to have.
156
393816
2305
你的聲音就會聽起來更好
06:48
Once you have those recordings,
157
396121
1673
當錄音完成後,
06:49
what we need to do
158
397794
1413
我們接下來
06:51
is we have to parse these recordings
159
399207
2718
要對這些錄音做語法分析
06:53
into little snippets of speech,
160
401925
2449
將它們分段,
06:56
one- or two-sound combinations,
161
404374
2337
大概1-2個音的組合,
06:58
sometimes even whole words
162
406711
1883
有時候也會是那些
07:00
that start populating a dataset or a database.
163
408594
4516
填入數據集或是數據庫的完整單字
07:05
We're going to call this database a voice bank.
164
413110
3717
我們將這個數據庫稱之為聲音銀行
07:08
Now the power of the voice bank
165
416827
2096
聲音銀行的力量
07:10
is that from this voice bank,
166
418923
2014
使我們通過它
07:12
we can now say any new utterance,
167
420937
2011
可以說出任何新的語句,
07:14
like, "I love chocolate" --
168
422948
1424
比如說, "我喜歡巧克力"
07:16
everyone needs to be able to say that—
169
424372
1739
所有人都需要說這類的話的能力
07:18
fish through that database
170
426111
1831
搜尋數據庫
07:19
and find all the segments necessary
171
427942
1940
找到必須的部分
07:21
to say that utterance.
172
429882
1929
來完成這個語句
07:23
(Video) Voice: I love chocolate.
173
431811
1789
(錄影)聲音: 我喜歡巧克力
07:25
RP: So that's speech synthesis.
174
433600
1391
演講人: 這是一個人工聲音
07:26
It's called concatenative synthesis,
and that's what we're using.
and that's what we're using.
175
434991
2573
我們將其稱之為連環整合
我們使用的就是這個方法
我們使用的就是這個方法
07:29
That's not the novel part.
176
437564
1533
這不是新奇的部分
07:31
What's novel is how we make it sound
177
439097
2221
它新奇之處是我們使它
07:33
like this young woman.
178
441318
1457
聽起來就像是這個年輕女士的聲音
07:34
This is Samantha.
179
442775
1524
她是珊曼莎
07:36
I met her when she was nine,
180
444299
2346
在她9歲時, 我第一次見到她
07:38
and since then, my team and I
181
446645
1897
在那之後, 我和我的團隊
07:40
have been trying to build her a personalized voice.
182
448542
2714
一直設法為她製造一款個性化的聲音
07:43
We first had to find a surrogate donor,
183
451256
3099
我們首先需要一個捐贈者,
07:46
and then we had to have Samantha
184
454355
1818
然後我們會讓珊曼莎
07:48
produce some utterances.
185
456173
1929
發一些音
07:50
What she can produce are mostly vowel-like sounds,
186
458102
2379
雖然她所發出的音大部分都類似母音,
07:52
but that's enough for us to extract
187
460481
2479
但我們用這些已足夠
07:54
her source characteristics.
188
462960
2285
來取得她聲音根源的特性
07:57
What happens next is best described
189
465245
3271
接下來所發生的事
08:00
by my daughter's analogy. She's six.
190
468516
2767
用我女兒的比喻來描述再合適不過, 她6歲
08:03
She calls it mixing colors to paint voices.
191
471283
5422
她說這是混合顏色來畫聲音
08:08
It's beautiful. It's exactly that.
192
476705
2555
很漂亮, 就是這樣
08:11
Samantha's voice is like a concentrated sample
193
479260
2860
珊曼莎的聲音就像是紅色食用色素
08:14
of red food dye which we can infuse
194
482120
2609
的濃縮樣品
08:16
into the recordings of her surrogate
195
484729
2540
我們可以將它注入到她代替者的錄音裡
08:19
to get a pink voice just like this.
196
487269
4387
然後取得一個像這樣的粉色聲音
08:23
(Video) Samantha: Aaaaaah.
197
491656
4491
(錄影)珊曼莎:啊.....
08:28
RP: So now, Samantha can say this.
198
496147
2808
現在, 珊曼莎可以說這個
08:30
(Video) Samantha: This voice is only for me.
199
498955
3069
(錄影)珊曼莎: 這個聲音是我的專屬
08:34
I can't wait to use my new voice with my friends.
200
502024
6305
我等不及與我朋友們分享我的聲音
08:40
RP: Thank you. (Applause)
201
508329
6417
謝謝
08:46
I'll never forget the gentle smile
202
514746
2333
我永遠都不會忘記
08:49
that spread across her face
203
517079
1902
當她第一次聽到自己的聲音時
08:50
when she heard that voice for the first time.
204
518981
3649
佈滿在她臉上那輕柔的微笑
08:54
Now there's millions of people
205
522630
1882
目前世界上
08:56
around the world like Samantha, millions,
206
524512
2833
有好幾百萬像珊曼莎的人, 幾百萬,
08:59
and we've only begun to scratch the surface.
207
527345
3440
而我們的工作才剛剛開始
09:02
What we've done so far is we have
208
530785
1642
我們目前只有
09:04
a few surrogate talkers from around the U.S.
209
532427
3859
幾個來自美國的語言代替者
09:08
who have donated their voices,
210
536286
1507
捐贈了他們的聲音,
09:09
and we have been using those
211
537793
1928
我們使用了他們的捐贈
09:11
to build our first few personalized voices.
212
539721
4472
來建造我們第一批個性化的聲音
09:16
But there's so much more work to be done.
213
544193
1756
但還有更多的工作要完成
09:17
For Samantha, her surrogate
214
545949
2188
對珊曼莎而言, 她的代替者
09:20
came from somewhere in the Midwest, a stranger
215
548137
3046
是來自美國中西部, 一個陌生人
09:23
who gave her the gift of voice.
216
551183
3841
送給了她一個聲音禮物
09:27
And as a scientist, I'm so excited
217
555024
2153
作為一個科學家, 我很開心
09:29
to take this work out of the laboratory
218
557177
1935
能將這個研究從實驗室
09:31
and finally into the real world
219
559112
1800
帶到現實的世界
09:32
so it can have real-world impact.
220
560912
3165
讓它產生一個實際的影響
09:36
What I want to share with you next
221
564077
1582
我接下來想跟大家分享
09:37
is how I envision taking this work
222
565659
2175
我如何想像讓這項研究
09:39
to that next level.
223
567834
2711
進入下一個階段
09:42
I imagine a whole world of surrogate donors
224
570545
3887
我想像著一個充滿了聲音捐贈者的世界
09:46
from all walks of life, different sizes, different ages,
225
574432
3260
他們來自各行各業, 有著不同的體型和年齡,
09:49
coming together in this voice drive
226
577692
3058
一起聚集到這個聲音活動
09:52
to give people voices
227
580750
2270
給其他人提供的聲音
09:55
that are as colorful as their personalities.
228
583020
3799
就像他們個性一樣多姿多采
09:58
To do that as a first step,
229
586819
2300
我們的第一個步驟,
10:01
we've put together this website, VocaliD.org,
230
589119
3275
是建立這個網站, VocaliD.org,
10:04
as a way to bring together those
231
592394
1624
通過這個網站將
10:06
who want to join us as voice donors,
232
594018
2675
那些願意捐贈聲音的,
10:08
as expertise donors,
233
596693
1772
願意提供意見的,
10:10
in whatever way to make this vision a reality.
234
598465
5339
還有想提供其它幫助的人聚集到一起
10:15
They say that giving blood can save lives.
235
603804
4153
有人說捐血可以救人
10:19
Well, giving your voice can change lives.
236
607957
4982
那麼捐聲音就可以改變他人的生活
10:24
All we need is a few hours of speech
237
612939
3050
從我們的代替說話者那裡
10:27
from our surrogate talker,
238
615989
1491
我們只需要幾個小時的語音,
10:29
and as little as a vowel from our target talker,
239
617480
4733
然後再從我們的目標說話者那裡取得幾個母音,
10:34
to create a unique vocal identity.
240
622213
3711
就可以建立出一個獨特的聲音身份
10:37
So that's the science behind what we're doing.
241
625924
2626
這就是我們研究背後的科學
10:40
I want to end by circling back to the human side
242
628550
4455
結尾我想再次強調人為因素
10:45
that is really the inspiration for this work.
243
633005
4102
因為它才是這項研究的啟發
10:49
About five years ago, we built our very first voice
244
637107
3699
大約在5年前, 我們為一個名為威廉的小男孩
10:52
for a little boy named William.
245
640806
2501
製造了第一個聲音
10:55
When his mom first heard this voice,
246
643307
2357
當他的媽媽第一次聽到兒子的聲音時,
10:57
she said, "This is what William
247
645664
2345
她說, "如果威廉可以說話,
11:00
would have sounded like
248
648009
1546
那他的聲音
11:01
had he been able to speak."
249
649555
2449
一定和這個一模一樣."
11:04
And then I saw William typing a message
250
652004
2418
我們然後看到威廉在他的設備上
11:06
on his device.
251
654422
1362
打一條訊息
11:07
I wondered, what was he thinking?
252
655784
3293
我猜想他在想什麼?
11:11
Imagine carrying around someone else's voice
253
659077
3590
試想一下借用了他人的聲音
11:14
for nine years
254
662667
2193
9年之後
11:16
and finally finding your own voice.
255
664860
4844
終於有了自己聲音的感覺
11:21
Imagine that.
256
669704
1377
試想一下
11:23
This is what William said:
257
671081
2797
這就是威廉說的話:
11:25
"Never heard me before."
258
673878
4463
"在這之前從來沒聽過我說話"
11:32
Thank you.
259
680417
1619
謝謝大家
11:34
(Applause)
260
682036
4724
掌聲
ABOUT THE SPEAKER
Rupal Patel - Speech scientistPeople relying on synthetic speech use the voice they’re given, not their own. Rupal Patel created the vocaliD project to change that.
Why you should listen
Northeastern University computer science professor Rupal Patel looks for ways to give voice to the voiceless. As founder and director of the Communication Analysis and Design Laboratory (CadLab), she developed a technology that combines real human voices with the characteristics of individual speech patterns. The result is VocaliD, an innovation that gives people who can't speak the ability to communicate in a voice all their own.
"There's nothing better than seeing the person who's actually going to use it, seeing their reaction, seeing their smile," says Patel.
Rupal Patel | Speaker | TED.com