[Applause] [Music]
or it is basically just a hole by their
or it is basically just a hole by their boot events so what’s happening right
boot events so what’s happening right
boot events so what’s happening right now is I’m manipulating the shape of my
now is I’m manipulating the shape of my
now is I’m manipulating the shape of my multi-track and that’s manipulating
multi-track and that’s manipulating
multi-track and that’s manipulating physics and having a whole bunch of
physics and having a whole bunch of
physics and having a whole bunch of acoustic events and you’re interpreting
acoustic events and you’re interpreting
acoustic events and you’re interpreting that at speech so one of the things that
that at speech so one of the things that
that at speech so one of the things that you could say happens in reception which
you could say happens in reception which
you could say happens in reception which is just you’re suing acoustic pattern
is just you’re suing acoustic pattern
is just you’re suing acoustic pattern matching you’re taking the frequencies
matching you’re taking the frequencies
matching you’re taking the frequencies that are coming out of my mouth your
that are coming out of my mouth your
that are coming out of my mouth your magic
magic
magic you’re saying I understand what it is
you’re saying I understand what it is
you’re saying I understand what it is that she’s saying and there’s a lot of
that she’s saying and there’s a lot of
that she’s saying and there’s a lot of evidence that that is what humans do we
evidence that that is what humans do we
evidence that that is what humans do we have auditory canal we have a bow chain
have auditory canal we have a bow chain
have auditory canal we have a bow chain because amplifies frequencies coming out
because amplifies frequencies coming out
because amplifies frequencies coming out of my mouth we have a cochlea that has
of my mouth we have a cochlea that has
of my mouth we have a cochlea that has hair cells that librarians sympathy to
hair cells that librarians sympathy to
hair cells that librarians sympathy to those frequencies that it’s connected to
those frequencies that it’s connected to
those frequencies that it’s connected to some auditory nerves that tells our
some auditory nerves that tells our
some auditory nerves that tells our brain which frequencies are being
brain which frequencies are being
brain which frequencies are being created and magically somehow if you
created and magically somehow if you
created and magically somehow if you hear a 300 Hertz and a 21-13 frequencies
hear a 300 Hertz and a 21-13 frequencies
hear a 300 Hertz and a 21-13 frequencies that you say she was produce right so we
that you say she was produce right so we
that you say she was produce right so we could say we’re just matching acoustics
could say we’re just matching acoustics
could say we’re just matching acoustics and there’s no reason like Siri can’t do
and there’s no reason like Siri can’t do
and there’s no reason like Siri can’t do that there’s no reason why Alexa can do
that there’s no reason why Alexa can do
that there’s no reason why Alexa can do that speech recognition should be a
that speech recognition should be a
that speech recognition should be a breeze well it turns out there’s a lot
breeze well it turns out there’s a lot
breeze well it turns out there’s a lot more that goes into it and that’s what
more that goes into it and that’s what
more that goes into it and that’s what I’ll try to convince you of today so
I’ll try to convince you of today so
I’ll try to convince you of today so we’ll start with this quick little
we’ll start with this quick little
we’ll start with this quick little experiment don’t let the sky play again
experiment don’t let the sky play again
experiment don’t let the sky play again and what is it what is it that you’re
and what is it what is it that you’re
and what is it what is it that you’re hearing
ah alright stop for one sec alright
ah alright stop for one sec alright we’re gonna play it one more time but
we’re gonna play it one more time but
we’re gonna play it one more time but what I want you to do this time just
what I want you to do this time just
what I want you to do this time just close your eyes all right close your
close your eyes all right close your
close your eyes all right close your eyes and here we go again okay you can
eyes and here we go again okay you can
eyes and here we go again okay you can open your eyes closed doing acoustic
open your eyes closed doing acoustic
open your eyes closed doing acoustic pattern matching you’re taking the
pattern matching you’re taking the
pattern matching you’re taking the acoustics and you’re brainless saying
acoustics and you’re brainless saying
acoustics and you’re brainless saying match those to a pattern
match those to a pattern
match those to a pattern I hear ba but when your eyes were open
I hear ba but when your eyes were open
I hear ba but when your eyes were open what was happening was you are also
what was happening was you are also
what was happening was you are also taking visual cues in in a nutshell this
taking visual cues in in a nutshell this
taking visual cues in in a nutshell this is called the McGurk effect and in a
is called the McGurk effect and in a
is called the McGurk effect and in a nutshell this is just your visual cortex
nutshell this is just your visual cortex
nutshell this is just your visual cortex messing with your audio cortex so what
messing with your audio cortex so what
messing with your audio cortex so what I’ll do for the rest of the day is try
I’ll do for the rest of the day is try
I’ll do for the rest of the day is try over the rest of my luck not the rest of
over the rest of my luck not the rest of
over the rest of my luck not the rest of the day you only have to say is to try
the day you only have to say is to try
the day you only have to say is to try to convince you that when the whole
to convince you that when the whole
to convince you that when the whole cerebral cortex gets involved it’s a
cerebral cortex gets involved it’s a
cerebral cortex gets involved it’s a mess it’s a big mess but it’s a useful
mess it’s a big mess but it’s a useful
mess it’s a big mess but it’s a useful mess all right so let’s go on to this
mess all right so let’s go on to this
mess all right so let’s go on to this next thing this is it easy what’s the
next thing this is it easy what’s the
next thing this is it easy what’s the past tense of how do you make a verb
past tense of how do you make a verb
past tense of how do you make a verb past tense in English
past tense in English
past tense in English Edie of course Edie what about spoken
Edie of course Edie what about spoken
Edie of course Edie what about spoken English what do you add yeah duck right
English what do you add yeah duck right
English what do you add yeah duck right hug
hug
hug past tense hug what do you add to kiss
past tense hug what do you add to kiss
past tense hug what do you add to kiss are you adding a D hearing a T right
are you adding a D hearing a T right
are you adding a D hearing a T right what are your adding to Wade you’re any
what are your adding to Wade you’re any
what are your adding to Wade you’re any good so you have two all right so it’s
good so you have two all right so it’s
good so you have two all right so it’s not Edie it’s actually at least three
not Edie it’s actually at least three
not Edie it’s actually at least three it’s actually a couple more but we’re
it’s actually a couple more but we’re
it’s actually a couple more but we’re gonna stick with these three right now
gonna stick with these three right now
gonna stick with these three right now so maybe what’s happening is you
so maybe what’s happening is you
so maybe what’s happening is you memorize
memorize
memorize in the English language and you memorize
in the English language and you memorize
in the English language and you memorize every single past tense that goes with
every single past tense that goes with
every single past tense that goes with those particular verbs but if I give you
those particular verbs but if I give you
those particular verbs but if I give you word you’ve never heard before each one
word you’ve never heard before each one
word you’ve never heard before each one of you is going to say the exact same
of you is going to say the exact same
of you is going to say the exact same thing about what the past tense of
thing about what the past tense of
thing about what the past tense of English is so the past tense of myth is
English is so the past tense of myth is
English is so the past tense of myth is mid mid sorry mid a sense of meet with
mid mid sorry mid a sense of meet with
mid mid sorry mid a sense of meet with the tea past tense of duck does it
the tea past tense of duck does it
the tea past tense of duck does it alright you know do this alright so this
alright you know do this alright so this
alright you know do this alright so this is something that you know about
is something that you know about
is something that you know about language that you didn’t even know that
language that you didn’t even know that
language that you didn’t even know that you knew and let’s do you think this is
you knew and let’s do you think this is
you knew and let’s do you think this is a little weird thing with the past tense
a little weird thing with the past tense
a little weird thing with the past tense same exact thing happens with the plural
same exact thing happens with the plural
same exact thing happens with the plural you all know the plural of English in
you all know the plural of English in
you all know the plural of English in English is to make a noun plural you
English is to make a noun plural you
English is to make a noun plural you just add a s what about what do you add
just add a s what about what do you add
just add a s what about what do you add to a cat s cats sure what about dogs
to a cat s cats sure what about dogs
to a cat s cats sure what about dogs that’s a Z and in fact most of the time
that’s a Z and in fact most of the time
that’s a Z and in fact most of the time we can make a noun plural you add a Z
we can make a noun plural you add a Z
we can make a noun plural you add a Z right so you think it’s an ass but it’s
right so you think it’s an ass but it’s
right so you think it’s an ass but it’s actually a Z and then to fish I don’t
actually a Z and then to fish I don’t
actually a Z and then to fish I don’t want to hear fish is the plural of
want to hear fish is the plural of
want to hear fish is the plural of fishes fish
and then you add right alright so yeah I
and then you add right alright so yeah I mean those right and then if I give you
mean those right and then if I give you
mean those right and then if I give you words that you’ve never heard before
words that you’ve never heard before
words that you’ve never heard before you’re all going to do the exact same
you’re all going to do the exact same
you’re all going to do the exact same thing all right so the personal thing
thing all right so the personal thing
thing all right so the personal thing that’s happening here is in our
that’s happening here is in our
that’s happening here is in our conscious mind we’re sort of
conscious mind we’re sort of
conscious mind we’re sort of oversimplifying things we’re saying at
oversimplifying things we’re saying at
oversimplifying things we’re saying at several that we know that when we have
several that we know that when we have
several that we know that when we have to add an alveolar to verb that ends a
to add an alveolar to verb that ends a
to add an alveolar to verb that ends a voiced sound a daddy voices at a t if
voiced sound a daddy voices at a t if
voiced sound a daddy voices at a t if it’s another IV later
it’s another IV later
it’s another IV later know just make it good all right say
know just make it good all right say
know just make it good all right say there’s a really set of complex rules
there’s a really set of complex rules
there’s a really set of complex rules that tells us the plural no let’s just
that tells us the plural no let’s just
that tells us the plural no let’s just simplify it and say that it’s s so one
simplify it and say that it’s s so one
simplify it and say that it’s s so one of the things that our brain does is
of the things that our brain does is
of the things that our brain does is takes this really complex system and
takes this really complex system and
takes this really complex system and simplifies it what do we do with the
simplifies it what do we do with the
simplifies it what do we do with the speech recognition system well we find a
speech recognition system well we find a
speech recognition system well we find a linguist and we say help us with these
linguist and we say help us with these
linguist and we say help us with these rules that are in people’s heads that
rules that are in people’s heads that
rules that are in people’s heads that they don’t know that are there because
they don’t know that are there because
they don’t know that are there because we’re going to need them to make our
we’re going to need them to make our
we’re going to need them to make our automated speech recognition system work
automated speech recognition system work
automated speech recognition system work well all right let’s do another little
well all right let’s do another little
well all right let’s do another little test here I’m going to just say a phrase
test here I’m going to just say a phrase
test here I’m going to just say a phrase what’s the phrase that I’m saying the
what’s the phrase that I’m saying the
what’s the phrase that I’m saying the last speech so the last speech well
last speech so the last speech well
last speech so the last speech well we’re at a TED talk so what you probably
we’re at a TED talk so what you probably
we’re at a TED talk so what you probably heard me say was the last speech all
heard me say was the last speech all
heard me say was the last speech all right but if we were driving down the
right but if we were driving down the
right but if we were driving down the coast and I said this is the last speech
coast and I said this is the last speech
coast and I said this is the last speech you wouldn’t hear it as speech you would
you wouldn’t hear it as speech you would
you wouldn’t hear it as speech you would hear in his speech acoustically the last
hear in his speech acoustically the last
hear in his speech acoustically the last speech and the last speech are exactly
speech and the last speech are exactly
speech and the last speech are exactly the same they’re articulate orally the
the same they’re articulate orally the
the same they’re articulate orally the same so their acoustic Li the same and
same so their acoustic Li the same and
same so their acoustic Li the same and what you do is you use the context to
what you do is you use the context to
what you do is you use the context to help you figure out whether you are
help you figure out whether you are
help you figure out whether you are Beach
Beach
Beach are you heard speech all right we do
are you heard speech all right we do
are you heard speech all right we do this all the time can we build this into
this all the time can we build this into
this all the time can we build this into a speech recognition system sure there
a speech recognition system sure there
a speech recognition system sure there are probability trees or decision trees
are probability trees or decision trees
are probability trees or decision trees that people are trying to build in the
that people are trying to build in the
that people are trying to build in the system saying if these set of words
system saying if these set of words
system saying if these set of words recognize then it’s more likely that
recognize then it’s more likely that
recognize then it’s more likely that this word is this and not this so it’s
this word is this and not this so it’s
this word is this and not this so it’s harder it’s more complex but we can
harder it’s more complex but we can
harder it’s more complex but we can build that into the system all right
build that into the system all right
build that into the system all right so you guys don’t have a problem with
so you guys don’t have a problem with
so you guys don’t have a problem with this because you understand that context
this because you understand that context
this because you understand that context is going to mean that I’m likely to say
is going to mean that I’m likely to say
is going to mean that I’m likely to say the next speech if we’re here at a TED
the next speech if we’re here at a TED
the next speech if we’re here at a TED talk and unless I’ve been nagging you
talk and unless I’ve been nagging you
talk and unless I’ve been nagging you the whole way down our lovely Drive of
the whole way down our lovely Drive of
the whole way down our lovely Drive of the coast you’re going to hear it as the
the coast you’re going to hear it as the
the coast you’re going to hear it as the last beach and at the last speech all
last beach and at the last speech all
last beach and at the last speech all right what else goes into this all right
right what else goes into this all right
right what else goes into this all right in the 1950s people started using kind
in the 1950s people started using kind
in the 1950s people started using kind of old-timey speech synthesis to do
of old-timey speech synthesis to do
of old-timey speech synthesis to do experiments on the human perceptual
experiments on the human perceptual
experiments on the human perceptual system one of the things that they did
system one of the things that they did
system one of the things that they did was they realized that they could change
was they realized that they could change
was they realized that they could change the precept of what vowel somebody was
the precept of what vowel somebody was
the precept of what vowel somebody was hearing by manipulating a certain set of
hearing by manipulating a certain set of
hearing by manipulating a certain set of things so one of the things that Varro’s
things so one of the things that Varro’s
things so one of the things that Varro’s what vowels are basically just kind of
what vowels are basically just kind of
what vowels are basically just kind of categorical boundaries in this big blob
categorical boundaries in this big blob
categorical boundaries in this big blob of acoustic space so yeah that’s just
of acoustic space so yeah that’s just
of acoustic space so yeah that’s just all a blob of a bunch of different
all a blob of a bunch of different
all a blob of a bunch of different acoustics based on almost an infinite
acoustics based on almost an infinite
acoustics based on almost an infinite amount of different acoustic patterns
amount of different acoustic patterns
amount of different acoustic patterns are showing up but your brain says
are showing up but your brain says
are showing up but your brain says divided the acoustic pie a certain way
divided the acoustic pie a certain way
divided the acoustic pie a certain way but the frequencies that come out of my
but the frequencies that come out of my
but the frequencies that come out of my vocal tract are going to be very
vocal tract are going to be very
vocal tract are going to be very different from the frequencies that come
different from the frequencies that come
different from the frequencies that come out of somebody else’s vocal tracts it’s
out of somebody else’s vocal tracts it’s
out of somebody else’s vocal tracts it’s completely dependent on the size of your
completely dependent on the size of your
completely dependent on the size of your mouth the size of your larynx how long
mouth the size of your larynx how long
mouth the size of your larynx how long your vocal tract is what kind of what
your vocal tract is what kind of what
your vocal tract is what kind of what your teeth are like all these kinds of
your teeth are like all these kinds of
your teeth are like all these kinds of things affect the frequencies so somehow
things affect the frequencies so somehow
things affect the frequencies so somehow we have to figure out a way as a human
we have to figure out a way as a human
we have to figure out a way as a human perceiver to make sense of this and one
perceiver to make sense of this and one
perceiver to make sense of this and one of the things it turns out that people
of the things it turns out that people
of the things it turns out that people do is they pay attention to what the
do is they pay attention to what the
do is they pay attention to what the range of frequencies are that are coming
range of frequencies are that are coming
range of frequencies are that are coming out of their interlocutors mouth so they
out of their interlocutors mouth so they
out of their interlocutors mouth so they synthesized with their old timey
synthesized with their old timey
synthesized with their old timey synthesizer the word bet all right if
synthesizer the word bet all right if
synthesizer the word bet all right if you have a vowel that sort of midway
you have a vowel that sort of midway
you have a vowel that sort of midway between bit and bet you want to see what
between bit and bet you want to see what
between bit and bet you want to see what people are going to perceive and it
people are going to perceive and it
people are going to perceive and it turns out if you put this word in the
turns out if you put this word in the
turns out if you put this word in the end of a sentence that has the top
end of a sentence that has the top
end of a sentence that has the top frequencies people are going to say I
frequencies people are going to say I
frequencies people are going to say I hear bet but if instead you have the
hear bet but if instead you have the
hear bet but if instead you have the bottom set of frequencies people are
bottom set of frequencies people are
bottom set of frequencies people are gonna say I hear bit in other words what
gonna say I hear bit in other words what
gonna say I hear bit in other words what people do is they calibrate their
people do is they calibrate their
people do is they calibrate their interlocutors vocal space they say
interlocutors vocal space they say
interlocutors vocal space they say here’s the frequencies that I hear and
here’s the frequencies that I hear and
here’s the frequencies that I hear and I’m going to contextualize all the
I’m going to contextualize all the
I’m going to contextualize all the vowels that they come out based on what
vowels that they come out based on what
vowels that they come out based on what I have calibrated for them there’s been
I have calibrated for them there’s been
I have calibrated for them there’s been lots of studies since the 50s with much
lots of studies since the 50s with much
lots of studies since the 50s with much better since speech synthesis showing
better since speech synthesis showing
better since speech synthesis showing exactly this so one of the things you do
exactly this so one of the things you do
exactly this so one of the things you do is you just say I hear somebody and now
is you just say I hear somebody and now
is you just say I hear somebody and now I’m going to do some calculations and
I’m going to do some calculations and
I’m going to do some calculations and use that information for how I interpret
use that information for how I interpret
use that information for how I interpret everything else that they say we can
everything else that they say we can
everything else that they say we can build this into a synthesizer – it’s a
build this into a synthesizer – it’s a
build this into a synthesizer – it’s a little trickier but we can just have the
little trickier but we can just have the
little trickier but we can just have the cyntha I means I’m sorry they a
cyntha I means I’m sorry they a
cyntha I means I’m sorry they a recognizer we can have the recognizer
recognizer we can have the recognizer
recognizer we can have the recognizer get the range of the pitch but somebody
get the range of the pitch but somebody
get the range of the pitch but somebody is producing and we can work that into
is producing and we can work that into
is producing and we can work that into our calculations do we do this at
our calculations do we do this at
our calculations do we do this at another level sure one of the things
another level sure one of the things
another level sure one of the things that happens is for most people males
that happens is for most people males
that happens is for most people males have longer vocal tracks and longer
have longer vocal tracks and longer
have longer vocal tracks and longer longer vocal cords than females what
longer vocal cords than females what
longer vocal cords than females what they have found in a lot of different
they have found in a lot of different
they have found in a lot of different studies is that just seeing a face that
studies is that just seeing a face that
studies is that just seeing a face that looks female that people have identified
looks female that people have identified
looks female that people have identified as female or people have identified as
as female or people have identified as
as female or people have identified as male changes the precept of certain
male changes the precept of certain
male changes the precept of certain things to give you one example the
things to give you one example the
things to give you one example the difference between sip and ship so the
difference between sip and ship so the
difference between sip and ship so the difference between and Shh
difference between and Shh
difference between and Shh it’s just where that band of white noise
it’s just where that band of white noise
it’s just where that band of white noise is first it’s in higher frequencies
is first it’s in higher frequencies
is first it’s in higher frequencies first it’s in lower frequencies if I
first it’s in lower frequencies if I
first it’s in lower frequencies if I synthesize a token that’s halfway
synthesize a token that’s halfway
synthesize a token that’s halfway between sip and ship I can try to figure
between sip and ship I can try to figure
between sip and ship I can try to figure out what it is people are going to do
out what it is people are going to do
out what it is people are going to do with that and one of the things that
with that and one of the things that
with that and one of the things that happens is if they think they’re
happens is if they think they’re
happens is if they think they’re listening to a female they say oh that’s
listening to a female they say oh that’s
listening to a female they say oh that’s ship
ship
ship if they think the very same signal is of
if they think the very same signal is of
if they think the very same signal is of coming out of a male mouth they say oh
coming out of a male mouth they say oh
coming out of a male mouth they say oh that’s sip in other words even before
that’s sip in other words even before
that’s sip in other words even before people have heard the frequencies coming
people have heard the frequencies coming
people have heard the frequencies coming out of
out of
out of their interlocutors mouths they’ve made
their interlocutors mouths they’ve made
their interlocutors mouths they’ve made some decisions about what kind of things
some decisions about what kind of things
some decisions about what kind of things will come out of that person’s mouth in
will come out of that person’s mouth in
will come out of that person’s mouth in order in other words they sort of pre
order in other words they sort of pre
order in other words they sort of pre calibrate and they do this with kids
calibrate and they do this with kids
calibrate and they do this with kids because kids are gonna have even smaller
because kids are gonna have even smaller
because kids are gonna have even smaller vocal tracts smaller vocal cords higher
vocal tracts smaller vocal cords higher
vocal tracts smaller vocal cords higher frequencies they tend to look at
frequencies they tend to look at
frequencies they tend to look at people’s height they tend to look at all
people’s height they tend to look at all
people’s height they tend to look at all kinds of different things about their
kinds of different things about their
kinds of different things about their interlocutor before they even open their
interlocutor before they even open their
interlocutor before they even open their mouth all right can we build this into a
mouth all right can we build this into a
mouth all right can we build this into a synthesizer sure I’m sorry I keep saying
synthesizer sure I’m sorry I keep saying
synthesizer sure I’m sorry I keep saying synthesizer recognizer speech
synthesizer recognizer speech
synthesizer recognizer speech recognition system can we build this in
recognition system can we build this in
recognition system can we build this in yes but the ramifications of this have
yes but the ramifications of this have
yes but the ramifications of this have been that for the first several decades
been that for the first several decades
been that for the first several decades of work on automated speech recognition
of work on automated speech recognition
of work on automated speech recognition male voices were recognized much better
male voices were recognized much better
male voices were recognized much better than female voices leading one of my
than female voices leading one of my
than female voices leading one of my colleagues to say in the early 90s I
colleagues to say in the early 90s I
colleagues to say in the early 90s I don’t know what it is about women they
don’t know what it is about women they
don’t know what it is about women they just can’t seem to be recognized by our
just can’t seem to be recognized by our
just can’t seem to be recognized by our machines so in any case we fixed some of
machines so in any case we fixed some of
machines so in any case we fixed some of this now so in the decades since it
this now so in the decades since it
this now so in the decades since it started we fixed some of this alright
started we fixed some of this alright
started we fixed some of this alright but here’s where it gets even more
but here’s where it gets even more
but here’s where it gets even more tricky if you’re building an automated
tricky if you’re building an automated
tricky if you’re building an automated speech recognition system we interact
speech recognition system we interact
speech recognition system we interact with people with all kinds of different
with people with all kinds of different
with people with all kinds of different dialects so to give you an example in
dialects so to give you an example in
dialects so to give you an example in Houston some people have marched it and
Houston some people have marched it and
Houston some people have marched it and ad in front of nasals in other words pin
ad in front of nasals in other words pin
ad in front of nasals in other words pin and pin are homophones you stick with a
and pin are homophones you stick with a
and pin are homophones you stick with a pin you write with a pen all right other
pin you write with a pen all right other
pin you write with a pen all right other people have that as two separate phone
people have that as two separate phone
people have that as two separate phone to separate lexical items pin pen all
to separate lexical items pin pen all
to separate lexical items pin pen all right
right
right who says pin pin who says pin pen well
who says pin pin who says pin pen well
who says pin pin who says pin pen well one of the things we know is that for
one of the things we know is that for
one of the things we know is that for Anglos older people are more likely to
Anglos older people are more likely to
Anglos older people are more likely to say pin pin younger people are more
say pin pin younger people are more
say pin pin younger people are more likely to say pin pen do people know
likely to say pin pen do people know
likely to say pin pen do people know this well if you do a perceptual test
this well if you do a perceptual test
this well if you do a perceptual test and give you something like rinse and
and give you something like rinse and
and give you something like rinse and rinse will also be homonyms if you have
rinse will also be homonyms if you have
rinse will also be homonyms if you have this merger they won’t if you don’t so
this merger they won’t if you don’t so
this merger they won’t if you don’t so you’re either rinse and rinse or rinse
you’re either rinse and rinse or rinse
you’re either rinse and rinse or rinse and rinse if I do a perceptual test
and rinse if I do a perceptual test
and rinse if I do a perceptual test ask somebody to choose what they’re
ask somebody to choose what they’re
ask somebody to choose what they’re hearing but I hooked them up to an eye
hearing but I hooked them up to an eye
hearing but I hooked them up to an eye tracker one of the things I might be
tracker one of the things I might be
tracker one of the things I might be interested in is where their eyes are
interested in is where their eyes are
interested in is where their eyes are going well if I put the picture of the
going well if I put the picture of the
going well if I put the picture of the older lady in the middle and say this is
older lady in the middle and say this is
older lady in the middle and say this is who you’re listening to it turns out
who you’re listening to it turns out
who you’re listening to it turns out that people’s eyes sort of move back and
that people’s eyes sort of move back and
that people’s eyes sort of move back and forth between rinse and rinse if on the
forth between rinse and rinse if on the
forth between rinse and rinse if on the other hand I put the younger picture in
other hand I put the younger picture in
other hand I put the younger picture in there their eyes go right to prints in
there their eyes go right to prints in
there their eyes go right to prints in other words you might not have known
other words you might not have known
other words you might not have known this at a conscious level but people
this at a conscious level but people
this at a conscious level but people react as if this information is in their
react as if this information is in their
react as if this information is in their heads I have an idea that older people
heads I have an idea that older people
heads I have an idea that older people are likely older white people are more
are likely older white people are more
are likely older white people are more likely to emerge this and younger white
likely to emerge this and younger white
likely to emerge this and younger white people are more likely to not so I’m
people are more likely to not so I’m
people are more likely to not so I’m going to use that information all right
going to use that information all right
going to use that information all right what do we do with this with this with
what do we do with this with this with
what do we do with this with this with an recognizer
an recognizer
an recognizer I’ll talk about that in just a second
I’ll talk about that in just a second
I’ll talk about that in just a second but let me give you one more example
but let me give you one more example
but let me give you one more example what else can we use well there is a
what else can we use well there is a
what else can we use well there is a feature of almost every dialect of
feature of almost every dialect of
feature of almost every dialect of American English that says instead of
American English that says instead of
American English that says instead of saying alveolar stop at the end of the
saying alveolar stop at the end of the
saying alveolar stop at the end of the word I can replace that with a glottal
word I can replace that with a glottal
word I can replace that with a glottal stop so instead of saying what I can say
stop so instead of saying what I can say
stop so instead of saying what I can say what so I didn’t break my time up to my
what so I didn’t break my time up to my
what so I didn’t break my time up to my alveolar Ridge in the second one and the
alveolar Ridge in the second one and the
alveolar Ridge in the second one and the first one I went what and bring brought
first one I went what and bring brought
first one I went what and bring brought my tongue to the my alveolar Ridge in
my tongue to the my alveolar Ridge in
my tongue to the my alveolar Ridge in the second one what I just closed my
the second one what I just closed my
the second one what I just closed my glottis but you probably all interpreted
glottis but you probably all interpreted
glottis but you probably all interpreted the second one as what so I guess all of
the second one as what so I guess all of
the second one as what so I guess all of the people of American English got
the people of American English got
the people of American English got together and said what how about if we
together and said what how about if we
together and said what how about if we just say that the grotto can stand in
just say that the grotto can stand in
just say that the grotto can stand in for the alveolar if it’s a teeth okay
for the alveolar if it’s a teeth okay
for the alveolar if it’s a teeth okay [Music]
and there are some African American
and there are some African American that stayed back and said you know what
that stayed back and said you know what
that stayed back and said you know what D is also an alveolar so how about if we
D is also an alveolar so how about if we
D is also an alveolar so how about if we make not only the T stand in for the
make not only the T stand in for the
make not only the T stand in for the alveolar offer they got up with the
alveolar offer they got up with the
alveolar offer they got up with the glottal stop but also D so good is
glottal stop but also D so good is
glottal stop but also D so good is interpreted as good but so is good if I
interpreted as good but so is good if I
interpreted as good but so is good if I stop things at the alveolar Ridge I mean
stop things at the alveolar Ridge I mean
stop things at the alveolar Ridge I mean at my glottis that can still stand in
at my glottis that can still stand in
at my glottis that can still stand in for a D let’s do that though just taking
for a D let’s do that though just taking
for a D let’s do that though just taking this same rule just pushing it one step
this same rule just pushing it one step
this same rule just pushing it one step farther okay that sounds good should we
farther okay that sounds good should we
farther okay that sounds good should we tell the white people for the Anglos
tell the white people for the Anglos
tell the white people for the Anglos that can only be SCT for the
that can only be SCT for the
that can only be SCT for the african-americans that could be SCT or
african-americans that could be SCT or
african-americans that could be SCT or sa ID if we put the dude on the right in
sa ID if we put the dude on the right in
sa ID if we put the dude on the right in the middle and say this is what you’re
the middle and say this is what you’re
the middle and say this is what you’re listening to people pick set if we have
listening to people pick set if we have
listening to people pick set if we have the dude on the left and say this is who
the dude on the left and say this is who
the dude on the left and say this is who you’re listening to people pick either
you’re listening to people pick either
you’re listening to people pick either said or set alright so this is probably
said or set alright so this is probably
said or set alright so this is probably a rule that you’re not aware you if I
a rule that you’re not aware you if I
a rule that you’re not aware you if I ask you what people do with alveolar
ask you what people do with alveolar
ask you what people do with alveolar stops if I ask you what the difference
stops if I ask you what the difference
stops if I ask you what the difference is between African American and European
is between African American and European
is between African American and European European American English you might not
European American English you might not
European American English you might not say this but it turns out people know
say this but it turns out people know
say this but it turns out people know this at some level so what do we do with
this at some level so what do we do with
this at some level so what do we do with our speech recognition system we kind of
our speech recognition system we kind of
our speech recognition system we kind of say this is there’s no way we can really
say this is there’s no way we can really
say this is there’s no way we can really build this into the model except to say
build this into the model except to say
build this into the model except to say some people might do this and some
some people might do this and some
some people might do this and some people might do this all right
people might do this all right
people might do this all right so perceived age of the speaker
so perceived age of the speaker
so perceived age of the speaker influences how we perceive things
influences how we perceive things
influences how we perceive things pristine ethnicity so does gender lines
pristine ethnicity so does gender lines
pristine ethnicity so does gender lines on a map and perceive disability and
on a map and perceive disability and
on a map and perceive disability and those
those
those three last ones are in red because we’ve
three last ones are in red because we’ve
three last ones are in red because we’ve done some experiments showing that in
done some experiments showing that in
done some experiments showing that in fact those things can even override the
fact those things can even override the
fact those things can even override the acoustic signal I did a lot of work with
acoustic signal I did a lot of work with
acoustic signal I did a lot of work with my people I grew up with in Michigan
my people I grew up with in Michigan
my people I grew up with in Michigan because one of the things that I found
because one of the things that I found
because one of the things that I found interesting was a lot of Canadian things
interesting was a lot of Canadian things
interesting was a lot of Canadian things that people were associating with Canada
that people were associating with Canada
that people were associating with Canada were creeping into anger speech in
were creeping into anger speech in
were creeping into anger speech in Michigan but the Michiganders were
Michigan but the Michiganders were
Michigan but the Michiganders were blissfully unaware of this so I had some
blissfully unaware of this so I had some
blissfully unaware of this so I had some lines and I that were produced by women
lines and I that were produced by women
lines and I that were produced by women from Detroit I played that in four
from Detroit I played that in four
from Detroit I played that in four Michiganders and I said I’m creating a
Michiganders and I said I’m creating a
Michiganders and I said I’m creating a speech speech synthesizer help me pick
speech speech synthesizer help me pick
speech speech synthesizer help me pick out the vowels that you hear if they
out the vowels that you hear if they
out the vowels that you hear if they thought she was from Michigan they did
thought she was from Michigan they did
thought she was from Michigan they did horrible why did they do horribly
horrible why did they do horribly
horrible why did they do horribly because Michiganders think that they are
because Michiganders think that they are
because Michiganders think that they are producing speech the way this was done
producing speech the way this was done
producing speech the way this was done back in the day Walter Cronkite talks or
back in the day Walter Cronkite talks or
back in the day Walter Cronkite talks or the newscasters talk when in fact
the newscasters talk when in fact
the newscasters talk when in fact there’s a huge violent that’s happening
there’s a huge violent that’s happening
there’s a huge violent that’s happening in the northern cities Cleveland Detroit
in the northern cities Cleveland Detroit
in the northern cities Cleveland Detroit Chicago places like that they don’t
Chicago places like that they don’t
Chicago places like that they don’t realize that this has taken place if
realize that this has taken place if
realize that this has taken place if from the other hand I lie to my
from the other hand I lie to my
from the other hand I lie to my respondents and say this woman is from
respondents and say this woman is from
respondents and say this woman is from Windsor Ontario then they hear exactly
Windsor Ontario then they hear exactly
Windsor Ontario then they hear exactly what it is that she’s doing so their
what it is that she’s doing so their
what it is that she’s doing so their belief that Michiganders use perfectly
belief that Michiganders use perfectly
belief that Michiganders use perfectly correct English overrides the acoustics
correct English overrides the acoustics
correct English overrides the acoustics I call this filtering out some of the
I call this filtering out some of the
I call this filtering out some of the acoustic signal the same thing
acoustic signal the same thing
acoustic signal the same thing unfortunately happens with our speech
unfortunately happens with our speech
unfortunately happens with our speech therapists one of the things that can
therapists one of the things that can
therapists one of the things that can happen if you have had a cleft palate as
happen if you have had a cleft palate as
happen if you have had a cleft palate as you can have what’s called hyper
you can have what’s called hyper
you can have what’s called hyper nasality and it turns out that if you
nasality and it turns out that if you
nasality and it turns out that if you show a picture of a client to a speech
show a picture of a client to a speech
show a picture of a client to a speech therapist and say diagnose the degree of
therapist and say diagnose the degree of
therapist and say diagnose the degree of hyper nasality in this person they’ll
hyper nasality in this person they’ll
hyper nasality in this person they’ll rate it as higher if they think the
rate it as higher if they think the
rate it as higher if they think the person has a cleft palate versus if they
person has a cleft palate versus if they
person has a cleft palate versus if they don’t I actually have a student right
don’t I actually have a student right
don’t I actually have a student right now that’s working on now augmenting
now that’s working on now augmenting
now that’s working on now augmenting what speech therapists do
what speech therapists do
what speech therapists do actually speech recognition because
actually speech recognition because
actually speech recognition because that’s one place that speech recognition
that’s one place that speech recognition
that’s one place that speech recognition can help it can help make sure that it’s
can help it can help make sure that it’s
can help it can help make sure that it’s an objective measure of hyper nasality
an objective measure of hyper nasality
an objective measure of hyper nasality versus subjective all right now what
versus subjective all right now what
versus subjective all right now what happens with the Michiganders they’re
happens with the Michiganders they’re
happens with the Michiganders they’re just out of luck they’re just gonna
just out of luck they’re just gonna
just out of luck they’re just gonna bliss way to go I’m thinking they also
bliss way to go I’m thinking they also
bliss way to go I’m thinking they also I’m like Walter Cronkite or Justin
I’m like Walter Cronkite or Justin
I’m like Walter Cronkite or Justin Bieber or something like that so just to
Bieber or something like that so just to
Bieber or something like that so just to finish up here we have this big great
cerebral cortex that we just use it why
cerebral cortex that we just use it why do we use it well we listen to speech in
do we use it well we listen to speech in
do we use it well we listen to speech in noisy environments all of the acoustics
noisy environments all of the acoustics
noisy environments all of the acoustics that are happening from the lights from
that are happening from the lights from
that are happening from the lights from the air-conditioning can mask some of
the air-conditioning can mask some of
the air-conditioning can mask some of the things coming out of my mouth so
the things coming out of my mouth so
the things coming out of my mouth so what happens is we use other things we
what happens is we use other things we
what happens is we use other things we use context we use vision we use
use context we use vision we use
use context we use vision we use everything in order to help us make
everything in order to help us make
everything in order to help us make sense of what our interlocutors are
sense of what our interlocutors are
sense of what our interlocutors are saying we listen to people with all
saying we listen to people with all
saying we listen to people with all different dialects so we have to kind of
different dialects so we have to kind of
different dialects so we have to kind of have some ideas about how these dialects
have some ideas about how these dialects
have some ideas about how these dialects work we listen to people who don’t
work we listen to people who don’t
work we listen to people who don’t perform speech necessarily the way that
perform speech necessarily the way that
perform speech necessarily the way that the dictionary says the Deuter that they
the dictionary says the Deuter that they
the dictionary says the Deuter that they were taught from their English teachers
were taught from their English teachers
were taught from their English teachers so we have to have a way of making sense
so we have to have a way of making sense
so we have to have a way of making sense of that and what we do is we engage our
of that and what we do is we engage our
of that and what we do is we engage our entire cerebral cortex so that if I say
entire cerebral cortex so that if I say
entire cerebral cortex so that if I say the end or the end or the end every
the end or the end or the end every
the end or the end or the end every child knows that the last one means that
child knows that the last one means that
child knows that the last one means that the talk is over but the sidewalk with
the talk is over but the sidewalk with
the talk is over but the sidewalk with the automated speech recognition system
the automated speech recognition system
the automated speech recognition system in their head shut down 20 seconds ago
in their head shut down 20 seconds ago
in their head shut down 20 seconds ago thank you very much
thank you very much
thank you very much [Applause]
[Applause]
[Applause] [Music]
”
Be First to Comment