[Script Info]
Title: 
[Events]
Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,♪ (Music fades in) ♪
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Chirping)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Vocalizations, different languages)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Talking overlaps in background)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Computerized beeping)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) We come into this world with the\Ninnate ability to learn to interact
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,with other sentient beings.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Child vocalizing)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) Suppose you are to interact with\Nother people by writing little messages.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) It'd be a real pain.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) And that's how we interact\Nwith computers.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,It's much easier just to talk to them...\Njust so much easier...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) If the computers could understand\Nwhat we're saying.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,For that, you need really \Ngood speech recognition.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Narrator) The first speech recognition\Nsystem was developed by Bell Laboratories
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,in 1952. It could only recognize\Nnumbers spoken by one person.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,In the 1970s, Carnegie-Mellon\Ncame out with the Harpy System.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,This was able to recognize over\N1,000 words and different pronunciations
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Narrator) of the same word.\N- (Man) Tomato - (Woman) Tomato
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Narrator) Speech recognition continued\Nin the 80s with the introduction of the
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,Hidden Markov Model, which\Nused a more mathematical approach
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,to analyzing sound waves that led to\Nmany breakthroughs we have today.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,You're taking in very raw audio wave forms
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,like you get through a microphone
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,on your phone
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,or (unintelligible)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Woman) We chop it into small pieces\Nand it tries to identify which phoneme
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,was spoken in that piece of speech.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Phoneme is a primitive unit for\Nexpressing words.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(voicing phonemes shown above)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,And then you stitch those together\Ninto likely words like Palo Alto.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Speech recognition today is good at\Ntranscribing what you've said...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man, to phone) What's the weather\Nlike in Topeka?
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) You can talk about travels, your\Ncontacts, like, "Where can I get pizza?"
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Phone) Here are the listings for Pizza.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) "Where's the Eiffel Tower?"\N(Phone) The Eiffel Tower is ...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Woman) We've made tremendous\Nimprovements very quickly.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man, to phone) Who is the 21st\NPresident of the United States?
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Phone beeps)\N(Phone) Chester A. Arthur was the 21st...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man, to phone) Okay, Google,\Nwhere is he from?
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) Years ago, you had to be an engineer\Nto interact with computers.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,Today, everybody can interact.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- One thing still in its\Ninfancy is understanding.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- We need a far more sophisticated\Nlanguage understanding model
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,that understands what the sentence means.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,We're still a very long way from that.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Beeping)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,♪ (Soft background music) ♪
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Woman) Our ability to use language is one\Nof the things that helps us have culture.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,It's one of the things that helps\Nus pass on traditions across generations.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,Figuring out how the system of language\Nworks, even though it seems easy,
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,turns out to be very hard, but is one that\Nevery baby understands by 2 years old.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Girl) There's two of them.\N(Woman) There's two Ls, yeah (spells word)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Language is extremely complex\Nand sophisticated...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- From the semantics
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- (Man in chair) Ironies...\N- (Woman) Strong accents...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- (Man) Facial expressions, human emotions...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Because that's part of\Nhow we communicate.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Humor...
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Aside) Do I have to careful\Nnot to offend the dinosaur?
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Language has so many different\Nlayers and that's why it's
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,such a difficult problem.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) The (unknown) human brain\Nand the learning algorithms in it
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,are far, far better at things like\Nlanguage understanding
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,and they're still a lot better\Nat pun recognition.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,- Whether or not we replicate exactly\Nwhat the brain does, to understand
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,language and speech, is still a question.
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Beeping)
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,(Man) For many years, we believed that\Nneural networks should work better than
Dialogue: 0,9:59:59.99,9:59:59.99,Default,,0000,0000,0000,,the dull existing technology