Merken

Possibilities for using speech and gesture recognition for the future of mobility

Zitierlink des Filmsegments
Embed Code

Automatisierte Medienanalyse

Beta
Erkannte Entitäten
Sprachtranskript
you
the same as
um I was so to speak english so I'll pick up in english so thanks
very much for having me here I'm quite excited to talk about my everyday work life and give you some insights on what we're doing on speech recognition and likes this will only talk about speech as the the other 2 speakers will be more on the the gesture topic so and I always laugh when I go in presentations to start with a short video so I hope that the goal here and some of you might know this video and actually 1 of my favorites is actually the best motivation and for some talking about speech recognition so and you might some of you might recognize it now in the public and of the it you think I think prove
this is the June cools blogs and
it was you knew what was
the end of the
soul and I'd like to talk to you about speech and recognition of something like this can happen in a
human actions but it deftly can happen uh when you interact between human and machine so as I'm a technical guy had to bring the phonetic representation of speech and recognition so this is really the the phonetics that you would see him and some of our documents that we have when we define and speech recognition systems so I'll talk 1st about speech so what is speech and and how do we have to use speech and the 2nd part which is the more important 1 for a for us is the recognition part and the understanding part so how do you get from from speech from understanding a language to really recognizing something with it and 1st of all of the the question I always have to answer
why do we care about speech interaction in the car and I'm I'm with Mercedes and you know all we have is every a big corporation probably we have this kind of brand cookie where we have different the market values or brand values of the main 1 for us the main ones for us that we get from always associated with the safety and comfort and safety is far as very important for the confidence well we make everything that our cars are safe and comfortable and when we talk about speech recognition those are the 2 values that we are working towards unsafe we always want to have the eyes on the road and the hands on the wheel and we want to make sure that the driver can really focus on what you really need to do drive as long as we're not autonomous and right now we have still not autonomous we really need to get the focus of the driver really on the road and that's what I really want to have the eyes on the road and the hands in the wheel about of course we want to as a liking for training and navigation music phone is really important feature also in the car we need to provide some simple access to entertainment features and to equal functions and that's when I really the the speech interaction is really uh piece for us that that brings us quite far so let's start with the basics but that sentence on the
top of as long as I have a job I always tell my boss that's why I'm here because speech recognition is really highly complex and it's a multifaceted and basically in the very beginning what you get is away from a 3 D space that is somewhat represented like this um the that of course requires you to have some microphones placed somewhere normally it's either in the ceiling somewhere war and and Maryland instead Miro and what I've put down here is that mobility increases complexity of because probably on you would ask yourself well theory doesn't Google doesn't and what is special about us some special let us is really that
we think we increase complexity now we
probably need to turn up the volume a little bit and I have just to a to make it a little bit more and to understand why it's more complex I have 3 or 4 of audio files the first one that I'm going to play known is basically a navigation command in a studio like environment FIL does start zooming of hoped was and from the so this would be a guy sitting in a studio having a microphone right in his hand uh again you probably never seen someone sitting has got a microphone right stuck in his face so all basically the same thing this is how it would
and basically come to us and when you're sitting in a car without any of the noise field such that z being Hochstrasser chances you might have heard of the volume is a lot less than than than we had before the next 1 I add a little bit speed of the vehicle to that context something out of a hundred kilometers so it's OK let's make a little bit faster than I thank I thank so you see I'm going to a machine and giving that kind of quality and that kind of noise makes it harder for us and that's why we're saying mobility increases complexity of so what we're basing the to do before we do any speech recognition we need to optimize that signal because that signal really is a pain for machines to interpret so what we basically do we have this and this wave of their we try to emphasize on the characteristics and try to get like more
smooth and an audio signal and the complex task we have to accomplish on the 1 hand road noise and air whether or not this rope on so you have a long road surface that has not really even so we need to think about this but of course also noise that we contribute to the windshield wipers turning signals uh those have all special frequencies that will disturb from speech recognition system so we need to think about how we intelligently can filter those old and last but not least in in dense traffic situations you through and also of uh cope with that so now let's assume we have dealt with that task and we have a clean signal that we can start to interpret next step for us is some get
something that the text or representation of the audio signal so don't care about languages German now but the
computer right now doesn't know you so it's just some text representation of an audio signal and so what I get here and funny to Mr. Wilson in Stuttgart is a texture representation of the underlying up there if we in the car only want to do a dictation of messages I think we probably could stop here but of course we need to be aware what is this what is language as an input to the system uh right now we do that by this 1 system setting and whatever the system setting is that will be the expected language that will be the input but if we do it in the future what we working on of course we would like to think about and and dynamic and automatic language detection also that's so that's quite a difficult task and there are a lot of institutes renowned corporations working on that but this would be like the next step but you don't even know that the system understands what language is spoken and even across languages the so um normally it just dictating messages in the car is not enough and we talk speech recognition because we want to solve tasks I mean that's what we're talking about confidence safety we wanna save to solve task and save time for the for the user so now we need to start and putting semantics and meaning to that language and now we are in the in the area of natural language understanding and when we talk about the meaning and and uh semantics we would know from how the German language and is set up we would know that father is a domain for navigation so the user probably wants to navigate somewhere and with the other filling words we would have like something appeal i which is just on on it and we would have that so that's basically where we want navigate to so now we are at a point where we can actually instructor system with in the car and what to do for us so and this is time for the different languages right now the chains getting that in our car we want to have a really the natural language understanding having said this
1 recognition technologies the the very early processing have improved to learn a lot in the last couple of years that's why also we have a strategy to partner with technology companies and even us at all although we are because the company and we can't do that all by ourselves and we want to participate on the latest developments that's why you would have to say I'm Parker with technology companies all focus lies really on the interaction in the dialog design to relieve the user experience with in the car and I wanna just give you some examples on what are the pain points also what we need to to think about 1st example
and intelligent dialog design solving tasks corporately cooperatively you might have usury before the end of every wrong series really it's set the benchmark and I'm I'm really happy with Serie because of a lot of folks on my work but but what Syria does in in many times and you you there does when it doesn't understand you award has some function it searches the web when you're driving at high 1 of 140 on the autobahn and you can just start with web search it's it's not meaningful for the user so this way for tablet or for something a stream that you have in our hands so it's it's a good way to do it in a car it's not a good way because you need to be cooperatively you need to give some options to the user so we would need to think about and translate this behavior how would this be within the car a 2nd 1 meeting user's expectations
and I stumble across this design amateur if you are aware of that it's like when the 1st Edison Electric Light got introduced and I love that they were trying to to delighted with matches instead of using the the key uh but notes on the on this side of the door and this translated to us means that in the very early stages of speech recognition and the vehicles and it's a domain and phone call and we have the options of dial a number and then you were able to dial a number of course 0 them 5 2 2 4 2 4 2 whatever and today this is not the user expectation more today they wanna talk about names nobody knows numbers anymore so today of course we need to be able to say or dial governmental and this is basically the number so of course we need to be very close to the market and user expectations and to see and what they want and how they really want to intuitively use the system um next 1 and that is probably 1 of the main
pieces we need to resolve ambiguities and so there are many many ambiguities and just for the example of noise dada uh city in Germany if you type in my should on Wikipedia you get a very very long list of knowledge that's in Germany so now the question is and it's almost never get to my start what are you doing the car you really need to intelligent design a dialog that corporate to the you get to where you want to be but I I I definitely say that today we are probably not there what we want to be there is still room for improvement on but I think those are expected the things where systems are good or where they fail and users don't accept them and this is why you really need a good dialog design next 1 also important um picture
yourself being the cookie monster of Sesame Street and you're sitting in a Mercedes um and you may just a cookies cookies cookies and what you expect the of the car to do in if you if you ask this is what will give you back 1st disobeyed big recipes with in the car and that really interesting for me that gives you back something about Wikipedia has some more details about cookies probably also that the best thing to do is you go down a little bit you get something to year of like Netscape you probably within that home page or within that website you would probably seen address of light uh like minutes all balls on the and the action and also so if you right now where and all 4 it would be quite interesting for the car to if you say copy cookie that the cartels you OK here's an address the 1 navigator like this and also of course if you are a somewhere today in Berlin it would be a little bit hard just for a couple of cookies to go to an over so that I would expect that the condescends I wanna bakery where can we get some coffee and using cookies so this is why I was saying we need the context of the car and this is 1 of our strength we have a lot of context we have parallel applications we know where the user goes in and always and we also have to know what other things are currently going on and the system and this will be a big hit an area of future where we're looking into how can we get this this context even better
um which challenges are we addressing right now which are which are probably coming within some of the next vehicle generations and 1 thing is speaker recognition and especially in our cars we normally have 4 seats and it would be quite interesting to think about what recognition for different seats because use cases might be very very different multiparty recognition from same thing you have and an open system an open microphone why don't you give the option to speak up to to any of the passengers and to and to also detect which seat is currently talking and maybe you have some settings that are special to that seat um keyword activation for speech activation I mean Google and Serie do it already so you can say hey you will OK Google his theory that is working again in our environment with all the noise we have around us that's a challenge so so we're working on this 1 um predictive user experience is something we're close looking into you and just as I said before the context is important
but in the context is the situation right now but there were context as before that can you learn about the user and adapt your speech in action in the your whole user experience based on the context you've learned before so we're trying to see whether we can work with machine learning mechanisms to really improve the speech recognition systems and then what have also already said before language makes so if you have different languages in the same dialog color can you cope with that we have 1 pretty good example on this 1 let's say the best class China which is 1 of obvious as plus markets there will be a normally a local from a person speaking Chinese in the driver sees and there might be someone not speaking Chinese them and the via PC them in the right hand side in the back so why would there be a possibility that 1 of them speeds English the other 1 speaks Mandarin was also the questions can you can assist them cope with that and how do we get there and last but not least and this I think perfectly fits into the session um can you talk about multimodality right now I've only talked about speech can the speech and the overall user experience be increased or improved if you add gesture to so if just point somewhere and then talk about it or if I if I add other modalities with it so this is also a topic where we where we get the different modalities together and see how we can optimize the the old system and so those are some of the things we are currently working on and looking into the of course there are also a couple of challenges we need to be very very aware of and we need to address the special attention
of privacy is 1 big thing for us
and you know if you talk about us you read will you do actually commission the cloud and everybody at some point has agreed that this was a vision in the quality is OK and that this data can be uploaded and of course speech in itself is a biometric information so privacy is a big issue here so you need to be very very careful what you really wanna to and why do you wanna do it so in the in the very best scenario you would have to go into the quality of course we know why they do it today in the called just because the computing power and the possibilities of the culture they are much much bigger but for us this means we need to think about it what is privacy how can we cope with privacy and how do we really informed the customer what we do with that data if we really need to do it the 2nd point your personality of speech interaction uh we've had a research project on this and whether it would be interesting to give oral speech engine a character I wouldn't it be interesting really to to speak with it and just like a natural interaction with the person we have very ambiguous and comments from our customers and that but some of them say yes interesting are the same no
it's a machine I don't want talk to him like a human so this is also something where do we go there you know serious serious very their personal and where do we wanna go there what's what's the character of or and system here availability another topic and then coming back to rule it's a Google again who currently works great if you have a network connectivity who does not work if you in a parking structure on the ground and you don't have a cell phone signal so for us and our customer expectations here again our system has to work even if we don't have a cell phone signal or or anything uh couple or no connectivity and last but not least this is always important will be as long as our our cars are driven by hand and much autonomous and this is dry restrictions that we follow very strict guidelines and this will be something we need to follow in the future as well so having said this and this brings me I guess to the end of hopefully a worthwhile
listen to the presentation went through much thank I think you and for your insights and
I think we're gonna make we're going to try and get the technology working for the next speaker was gonna supported what you just said thank you very much thank you it nominal 7 and but this waiting for us he has already sent word that she is ready let's hope
that the Internet and helps those without on the paper so I heard her and in a workshop actually in Texas when she was giving advice about your online digital body language and and I had not been familiar with this topic before and she talks about an stuff you're not aware of like when you choose your profile picture what does it say about you she actually has some tools where you can evaluate that and it's all about gestures and and phase and mimics that you do or that expressible things that you're not just through someone's of consciously doing and you're not all awake again if you weren't but it works OK OK so and to get some advice on how to pick your Facebook profile picture for example and to think about what you want people to think about you when it comes to your profile what do you want to express what you want them to know about you will all who do you want to be and she has some advice on how you can do that and I'm just telling you more about the works of and it's also about figuring out what kind of personality you are and what you are compatible with I guess also when it comes to a jobs or your website for example she has a really interesting way of and of putting erect side of whether the science of people because she's running allowed where she's actually looking into digital body language and researching it to figure out how it all works and then you see in this lecture looks at lots of things for example of course you know all the theory about the colors and what they mean but she thinks that also your target audience reacts to different colors and then she is going to go to the to the left up to say hi
I'm allowed to
I mean that's now we can see you and you you know on a very extreme with it but you full full screen Greenspot problem so I told the people a little bit about your background and about the workshop I was lucky to attend in Texas about digital body language and I think they're all warmed up for you now and you can just go ahead we just heard a little bit about gesture control and in the cart of the future and today and now we're interested to hear about your perspective on the story great I'm just trying to share my screen although 1 moment share Fourier yeah the next morning would be 0 already the height you got my screen on your
industry yes are rational screening the hopefully about achieving full screen for you not yet no we can see your of your Skype wrapping can you can you make it full screen and them up OK then we're having at that this alright so wouldn't you then so I'm very happy to be here today and talk a little bit about digital body language and what visual body language is is ah nonverbal cues with in our mobile devices acts and and what we like to integrate human behavior in the
technology and and so what we do irrational behavior research lab in Portland Oregon ends and we take a latest human behavior research on how we use our technology in and integrate that into the user experience and usability so very briefly and since I only have a few
minutes now I wanted to talk about what makes a is by language there actually 10 different laws of human behavior within body language that were in talk about most important three-day and when we're talking about nonverbal cues were talking about logos picture as many pages I did use user interface and colors and fonts is sort of the assets that peak out digital body language on the flip side of those
assets draw US states cause us to change our percept our perception of a brand's 1st impression the trust indicators of operand the brand values the brands credibility and memorability and then of course the purchase decision if someone decides to click or by or stay without war or a mobile interface and then
loyalty it up and that's what those visual cues bring out very briefly about 1 thing that I would start with just to show the
impact as nonverbal is and this slide all the different bases so 1 study was done at test adversity finally neon body and what she did was she wanted to know what kind accuser sent by the and as we know in our in our mobile experiences we see pictures all the time whatever in dating out so we have that I want to parser profile pictures and we don't realize how many cues are being sent off small pictures so what she did was she devised a very clever experiment where she hybrid people look at use of of a grid of faces she high and then try to guess who is the most influential now all the pictures you see in front of you are taken from this Fortune 500 list some of the CEO's in front of you are the top members of the Fortune 500 list in other words they're the most successful influential and some of them are from the bottom of the Fortune 500 list and what they did was we wanted to know the his books could tell just by looking at picture which with the CEO's were the most and least influential and people were accurately able to do it they're able to glance at a picture and guess who had the move made the most money in the in the least money and here's the trick with this study is the longer they let someone look a face the worst their rates stocks so for the last few minutes at my this picture up in even hopefully second-guessing your guesses on who you wanted to be thought was the most influential so let's actually played I came about as player right now so here 3 different pictures of
CEOs I want you to guess who you think is the most influential it's a B C you can raise your hand if that is ahead of you think it's the phrase it had that C so the answer is the now most people the majority people can guess she but the the trick is that we have to show that the very very quickly as what we found was in our lab is is works on Twitter as well so what we did is we replicate this experiment we pulled
random pictures of people on Twitter and we showed that our users in our lab these 3 different pictures and we ask them how based on their photos who do you think has the most followers on Twitter and we found again the longer we left this out but hopefully right now you're looking at this these images in your second-guessing yourself you're trying to figure out who has the most followers so how many people think it's a however looking at speed I will at sea so the answer is OK now I love this up for quite a long time so media not striking the audience the cancers were sorted evenly split that's very common the longer the the the next laminar do that we have another very quickly so what it gets answer and stick to it your media got reaction this is the man so of these next 3 matches and how many do you think who has the most
scholars have better handling of a Our involving as being look now looking at sea so the answer is B. and we found the faster we show these pictures the more people can guess at when you're on a mobile device in your school refectories see someone's picture Avatara usually you're looking at those pictures for less than effect and you make it so many of your unconscious decisions based on a nonverbal cuing those pictures and that's what I wanna talk about
today but I wanna talk about the patterns that we found it make people think someone who is more influential or more popular or more likely to be trusted and those that are less likely to Boston so we can learn that users from pictures that are more likely to be trusted and this is a lot of folk got make a expression so today is a and
2010 set aside a focus on the face is a lot of cues we talk about with the face is the most powerful 1 and want about half the talk about the biker expression so micro expressions is a very quick facial expression that we all make we feel intense emotion it's in Monterrey so we make it no matter what worked on we cannot control that very quick my patrician happens in about 1 20th of a 2nd very very fast we found is that what you're watching a video on your forehead where we near picture are breaking is constantly scanning for these facial actions
I want to point out that actually 7 universal facial expressions today I wanna talk about my favorite stop especially in the mobile world the most and because they're the ones we really have to watch out for to the 1st of my best the we should all be able to recognize and hopefully eradicate from any of our other experiences on on the on the lookout for its content so Constantz is they work 1 site in all 3 is and it's kind of like a small if when someone found holes that now away at the eyes kind and aero at someone I n the importance of is that it is an incredibly powerful
facial expression you know it's really simple most of us think that as the contender this mark is a partial smart but it that the more opposite than partial smile contempt is being traded sustain estimates of and so what should have was this researcher John Gottman Dr. John governors a marriage and family counselor in Seattle and he um without realizing it discovered the power of a smirk what he did is he wanted to look at 1 of our I think because questions and the marriage world which is why do couples interval so what he did was he studied a few thousand cup he brought them in the lab you tested them on everything he could think of yes it down on top of here samples urine samples well it will even personality testing era QTS test keep up the you tape and interacting gave that the interview their friends and families and kids and then he followed them for 30 years what he was looking for was pattern see why did some people get worse like some couples together what he found was at the very end of the experiment is it the couple then got divorced mediates small swear constraints make expression in the very 1st intake interview In fact it was so powerful this not it he can predict with that the 3 . 6 per cent accuracy which couples will divorce in 30 years just by hurt tense so when we're designing things were looking at pictures we have video so we have Intro videos we have to realize that on small Östberg is like plans as he did this respect it is very difficult to build brand loyalty to get purchase decisions and say give user plus expect and whatever you have contempt Torres works fine any of your pictures but just go on where to write Stalin who go you're and profile of and put a picture face the picture and check and make sure you don't have a smart I would say at least 40 per cent of the pictures that I see in social media include a smart people don't even realize what they're set you'll see this in celebrities that
bother us so a lot of celebrities
that's I use the contempt maker expression a kind of a great honor is they irritate us a little bit and the here in the
US it when politicians show contends the approval ratings dropped so it's also very and powerful cue Stewart brand personality array of loans next profession and this 1 is happiness
so guess most people think is very simple if they happen is just a or on the trick happiness so it's actually not think happiness the only true indicator happiness is when the smile which is all the way up in the side of our eyes little muscles in the size of our eyes that will bomb all this the crow's feet wrinkles so you'll notice in these videos the difference in a fake smile and a
real smile so in the fake smile you have someone so all way up to the eyes you can tell that she was all derived and the bills smiles judge the real scientific smile she i just leave it in the bottom half of her face so we know that when you're taking profile pictures when you're in video in authenticity world laughter patch from back of engagement comes when people see a fake smile considerable so it's kind of a trigger for people to go but she's not a brand that I can relate to this is not a real Brandes non-authentic band is is not a brand I could trust and this is the Bohr orbit brands being or great pictures and photos even stock images and also individual personalized avatars and photos so this universe is real as 1 of the easiest ways to show authenticity what we
found is that celebrities who have not Botox or their smile a lot of selectional Botox event process surgery so that the smile the authentic smile ripples appear we see the mistake at pose an authentic where celebrities that use their entire face we really like that
because we see them as of take and site that
next door neighbor you really wanna be friends with them they have this really whole some loyal brand where is all the celebrities who have got Botox wrinkles
in don't smile way up into their face we see in a certain in authentic and especially
politicians here the that don't smile at their full face in very bad ratings so but how some about
number 3 is is fear and is letting 1 of artists once a spot because we don't realize it's happening so fear from an evolutionary perspective is when people in their eyes rock their mouth open and raise your ire up at the right it's when you see the whites of someone 5 I will will tell me enough that been on a business world no 1 is showing here during business or no one's showing fear
in their profile picture in the videos the problem is is that we actually show fear for ages about someone's taken a photo sometimes we can accidentally show fear when the light is to aid in our pictures or videos and so what happened is is that not only does this year of your picture shown anxieties what makes you look like or a low confidence are low confidence but also produces anxiety for example I have these 2 videos playing and as you watch the you should actually begin to feel a little bit anxious the reason for that is it's called the facial feedback hypothesis and is that our brain nearest what was so when you see a fearful face you actually begin to feel that fear with its of of aces the so you have in any in any way shape or form can also be in cartoon characters Avataras stock images videos it actually begins to produce fearing the user
the so you see that sometimes in
pictures were people have widened their eyes just a little bit above other people's you see the whites of their eyes so you see this over and over again with different
pictures and he will choose these photos without realizing that what they're showing is a deep kind of anxiety is also can happen in
the US and people using an oval devices more and more to what can watch consume all kinds of video content people can accidentally show fear when a for deadlines when they stage flight sometimes TelePrompTers what's that produce feared based on where they're placed camera nervousness even uncomfortable clothing when women are wearing high heels than having their sitting as skills never be heard that will actually show up in the facial expressions through pain or fear and of course difficult past whatever I'm watching news interviews you'll often know when someone is very nervous that cancer because they flashlights advisory before they answer
I'm not 1 of things you can see in action I'm not able to cover all the different facial expressions here the 7 universal facial expressions your welcome to go to sites labeled up from slashed head this season work artificial special analysis of videos I wanna show 1
really quick video hopefully will come through and most people don't believe me that facial expressions that happened very involuntarily and more importantly we can jump from 1 extreme facial expressions the next extremely quickly so this is a video and its video the baby's watching it it's Mom below her no and this delight and terrifies the baby at the same time that I want you to watch for the 2 facial expressions we just learned happiness and fear and see how quickly we go from 1 to the next there is no clear and
found that that had had had their and so I had to know and if you don't have that would have to this is a in the bad and the head and the Moon know here we will never have to over the years now if other this a uh at home for free head
OK know that it is going to reduce the long although we love watching it so as you can see it in that area that they didn't even have eyebrows yet yet we were able to recognize that Apple's about smile at that well reach all the the size and the era when we see the way of the baby's eyes so this is a very silly ample this comes rocks in every kind of image that were showing our mobile devices or even on our website were profiles whether that's a picture of Archean Avatara or even a depiction so what 0 challenge you do is think about how can you eliminate fake smiles fear icon's Smirks and how can you add a genuine smiles call Miles and In addition you have a images or videos in your eye in your mobile experience adding a genuine smiles communizing even smiles can actually greatly increased the other digital cues authenticity the your
sending out now want to look for a 2nd about directional actions and this is a different part of digital cues of how we take action as if in a mobile experience for hoping to direct action clips the use eating purchasing look where a lot of that comes from so the 1st thing credit
which tend to take she is from other people's eyes more than thing and we forget this sample experience because oftentimes we don't have as many pictures or we don't have as much space but the most power full where you can interact she is is used in other people's ideas and this in a couple different ways 1st
most of his out about the same that we make a general I pattern on a website despite a pointer incident that we were looking at a website where we tend to call gaffe power we start up at the upper left-hand corner we move across the top of the page then we scroll down over aircraft down again I think it is very important so and 1 thing that we found is that it's here in natural for people to
other have come into the
Napoli for example here is the website by repeats a he uses the F-pattern as well as some open by ideas to prompt action so you that he is that his own face up to the upper left-hand corner and immediately he's looking at all it to the side where you actually go to his headlines are you ready to live a rich life so he falls into a natural at pattern as well as making we want to follow the you ever been standing on the street in you I look at the sky he notices people walk by the H. help but also look up for the sky that is because we're all as human to follow other people's action he use that natural tendency to be able to fall into where we want to go to not only is he looking over his his headline are you ready to leverage but is also looking over his buttons where he wants you click that happens again find the same job we want you to get started this happens all over again
with different websites where they have a feast and they direct the eye-gaze topics the headline and even this 1 you have the uh the headline up talking you have the female the bride looking back the headlines you're more likely to read it and she has to go back for the blind to it directs your days back exactly what you want someone to do the so we use this
all across the website we played with different things so here's a post factum of signs of life would then we teach our lab we study if your life should so I'll use gaze and try to
see how I can get people to change their gaze and change their actions based on where we are looking at are pictures you can
also do this gestures so let's say that you don't have some pictures of faces is in your experience she'd even do this with different and gestures the so for example of this what's the website by more before Leo she actually uses 4 fingers to point where she wants you to look at as well as the what's going and then
she all you also see in other pictures the user
gestural hand but these pencils pointing toward the and graphic design geniuses to sort of gesture over where they want you know read and click the
our highest see now a part of this and so had this last thing is just where you view this little monkey is not even a real person down without the bottom with the user's we're flashlight gesture to be able to show 5 is that they want you read you have the right to know they use gestures a interesting
way to hearing challenge to eliminate confusing these cues any gazing away from content and adding into natural of patterns the gaze and gesture headlines and gazing ingestion Burke
and for work action so at the end here with a couple of things so I'm again he's written by my sort of favorite was a visual human behavior I will actually having a free webinar all this you're welcome to join if you want as well they have all these tips online I challenge you to think about what your body language cues are in your mobile experience and when you're using other people's acts so it's not just for your own experience it also works when you're using acting you see pictures are see gestures or videos how is that affecting the how is that changing your perception of that branch because just tuning into how that affects you can really change your experience The granite the best way to learn to see how pictures change things I also challenge you to out please look at your LinkedIn profile picture your Facebook profile picture and your Twitter profile picture and make sure that you're not shown it contends or in authentic smile or any theorize because that is changing your personal brand to signify things that are more negative I'm and less positive so I get any question but also the hop on Twitter right now and I'm not there to take any questions on twitter if you have any for me thank you for your attention all these things and it's really terrifying when you know somebody like you can totally know what you're thinking subconsciously so I'm just going to pick up and out and the workers have again as stuff onto a high and you actually have a super cool newsletter as well dead people can subscribe to Lady teach people more things like that thank you so much the thank you and and for the last part of our session we're gonna have there and the presentation of art for the future of mobility and you have your your microphones we that honor be turned on the worry about it and we actually have helped that's gonna translate for us I'm what
Mathias Schäfer was the artist is gonna perform fast yeah and but will also going to have the text on the screen so you can fully give yourself to this experience of gesture and they're the journey that has created for us and really looking forward to this have fun
and I think you and they found an aside I would like to introduce myself yeah my name is matt yes and I'm going to
and speak German signing which this on I to interpret as they're going to speak in for you thank you the yeah I was going that's and so when
I when a graph I didn't hear anything so I don't know so I grew up and i'd god of information through my eyes good the put their signatures of the body language this is a I N how with everything and so I'm going to show you to have a story with where I guess chairs and and the makes other impart they're going to have show you how you could maybe driver correlated with mimic OK so the so I'm going to use my
facial expressions and food they have some meanings and then a grammar meaning also German Sign Language then I have to move my my body and my my hat also has a meaning and also I have my my hands and they're 38 hates different handshapes and the German Sign Language they meaning yeah and there's also was called something like classifiers and and this I tend to think
that that directly take action and like Pentomino some something similar similar and and I would like to come the if you don't understand everything just just let the gestures and makes that I made it gives you a feeling of what what might be the content of my performance the there's only past that will be written there's more in and and and the interpreters just the short parts of the but there's no constant and wouldn't assigning the or just tree in
so I go to sleep at the end of I have this dream but I'm floating up from my bed going faster and faster until all of in the this guy is covered by dense clouds and I'm I'm I'm flying through the clouds and i'm flying through the clouds and when the sun will rise from the horizon of and
it will certainly
of because of there's a down I slowed down to fly through this again my site opens up and have to have a big city there's many high-rise buildings and notice in the news every land and and
I like deeper down to its the city center land in the middle of an empty analyze those where I find myself being surrounded by skyscrapers the the between skyscraper was the
day's 1st rays of sunshine breakthroughs and there is like phenomena is 1 of the
things that all these windows are coded with transparent so the cells and they the energy to underground factories and things as I look around me all is urban canyons the thing there is known to be found around me find wide link emptiness I raise my right arm to hit my watch arranging the signal given out by MacArthur centers satellites in supersonic speed having received at the satellite sensor signal so as to remain computer which is situated in the territory of shape prior but
the 1 of them is activated it's taken that was by an elevator and then it starts moving independently and travels on the roads in 1 direction and
interview perspective you can see it's taking its way through the city is heading to its meaning in and out of from a distance of I ICT to coming in and they do it in a way that's right and at the end yeah the action current gently pulls over and stops in front of me Jonas OpenupEd widely inside and kind of there's
seemed to build in round circle they're made of shiny white leather in the center there's a table with around touch screen surface as I get on the kind the doors close behind me on the
touchscreen table right engine atlas and with the lights on and off the crash starts moving the suddenly life comes back to town everywhere I see people and exchange currents everything is in motion then no traffic lights no traffic jam yeah so there's a central computer controlling the traffic flow yeah it is a good and safe feeling the the through a circular
panoramic window I observed all this with amazement without realizing that the next shape prior brings me closer and closer to my desired destination having reached my destination I get out of the car
there's a beautiful woman waiting for me I asked her if she would like to go to the instrument she just shakes her head and smiling she points the finger at the exact time I isomer that and look my head like that we both get the doors chanting close and the kind of drives away into an unknown destination high-ranking and it's my about stream then I think why not and the let this future coming and on the internet forums and yeah it thank you thank you very
much and this is the end of our session thank you so much for attending you can always visible stall at the beginning of the whole of the dataset and ask us more questions there thank you so much for your attention had a great time here the Republic and
and
Hypermedia
Videospiel
Lesezeichen <Internet>
Besprechung/Interview
Vorlesung/Konferenz
Sprachsynthese
Kombinatorische Gruppentheorie
Mustererkennung
Mustererkennung
Computeranimation
Videokonferenz
Benz-Ebene
Selbstrepräsentation
Gruppenoperation
Formale Sprache
Sprachsynthese
Sprachsynthese
Physikalisches System
Mustererkennung
Computeranimation
Virtuelle Maschine
Formale Sprache
Einheit <Mathematik>
Mereologie
Vorlesung/Konferenz
Wellenpaket
Multiplikation
Interaktives Fernsehen
Sprachsynthese
Kolmogorov-Komplexität
Komplex <Algebra>
Raum-Zeit
Physikalische Theorie
Computeranimation
Eins
Bereichsschätzung
Prozess <Informatik>
Gruppe <Mathematik>
Speicherabzug
Lineares Funktional
Mobiles Internet
Sprachsynthese
Mustererkennung
Fokalpunkt
Druckertreiber
Differenzkern
Funktion <Mathematik>
Benutzerschnittstellenverwaltungssystem
Cookie <Internet>
Mustererkennung
Bit
Multiplikation
Wellenlehre
Mobiles Internet
Sprachsynthese
Geräusch
Kolmogorov-Komplexität
Sprachsynthese
Mustererkennung
Kontextbezogenes System
Komplex <Algebra>
Audiodatei
Computeranimation
Virtuelle Maschine
Datenfeld
Rechter Winkel
Vorlesung/Konferenz
Spezifisches Volumen
Mustererkennung
Programmierumgebung
Multiplikation
Selbstrepräsentation
Formale Sprache
Sprachsynthese
Geräusch
Sprachsynthese
Physikalisches System
Mustererkennung
Frequenz
Computeranimation
Dichte <Physik>
Task
Mustererkennung
Domain <Netzwerk>
Multiplikation
Punkt
Prozess <Physik>
Formale Sprache
Selbstrepräsentation
Interaktives Fernsehen
Sprachsynthese
Computer
Computeranimation
Formale Semantik
Task
Textur-Mapping
Domain-Name
Bereichsschätzung
Fokalpunkt
Softwareentwickler
Bildauflösung
Sprachsynthese
Physikalisches System
Ein-Ausgabe
Mustererkennung
Fokalpunkt
Natürliche Sprache
Wendepunkt
Verkettung <Informatik>
Menge
Flächeninhalt
Strategisches Spiel
Wort <Informatik>
Mustererkennung
Message-Passing
Lineares Funktional
Reihe
Mathematisierung
Systemaufruf
Zahlenbereich
Sprachsynthese
Physikalisches System
Mustererkennung
Dialekt
Computeranimation
Konfiguration <Informatik>
Task
Streaming <Kommunikationstechnik>
Benutzerbeteiligung
Erwartungswert
Domain-Name
Task
Verbandstheorie
Mustervergleich
Tablet PC
Benchmark
Erlang-Verteilung
Web Site
Bit
Machsches Prinzip
Adressraum
Güte der Anpassung
Gruppenoperation
Vierzig
Bildauflösung
Geräusch
Mailing-Liste
Kartesische Koordinaten
Physikalisches System
Kontextbezogenes System
Kontextbezogenes System
Computeranimation
Homepage
Monster-Gruppe
Task
Navigieren
Flächeninhalt
Datentyp
Cookie <Internet>
Subtraktion
Multiplikation
Punkt
Formale Sprache
Gruppenoperation
Klasse <Mathematik>
Besprechung/Interview
Geräusch
Maschinelles Lernen
Sprachsynthese
Physikalische Theorie
Virtuelle Maschine
Prognoseverfahren
Unimodale Verteilung
Kraftfahrzeugmechatroniker
Sprachsynthese
Reihe
Prognostik
Gasströmung
Physikalisches System
Kontextbezogenes System
Mustererkennung
Konfiguration <Informatik>
Modallogik
Generator <Informatik>
Druckertreiber
Menge
Offenes Kommunikationssystem
Formale Sprache
Rechter Winkel
Kantenfärbung
Mustererkennung
Programmierumgebung
Mooresches Gesetz
Datenmissbrauch
Punkt
Interaktives Fernsehen
Projektive Ebene
Sprachsynthese
Information
Maschinelles Sehen
Datenmissbrauch
Streuungsdiagramm
Biostatistik
Computeranimation
Einfach zusammenhängender Raum
Virtuelle Maschine
Erwartungswert
Datennetz
Autonomic Computing
Hill-Differentialgleichung
Physikalisches System
Kombinatorische Gruppentheorie
Druckertreiber
Datenmissbrauch
Computeranimation
Web Site
Facebook
Formale Sprache
Profil <Aerodynamik>
Physikalische Theorie
Computeranimation
Internetworking
Prozess <Informatik>
Digitalisierer
Vorlesung/Konferenz
Wort <Informatik>
Kantenfärbung
Ereignishorizont
Phasenumwandlung
Bit
Momentenproblem
Gemeinsamer Speicher
Perspektive
Digitalisierer
Formale Sprache
Entscheidungsmodell
Gamecontroller
Vorlesung/Konferenz
Touchscreen
Bit
Digitalsignal
Benutzerfreundlichkeit
Irrationale Zahl
Digitalisierer
Formale Sprache
Visualisierung
Computeranimation
Touchscreen
Schnittstelle
Subtraktion
Benutzeroberfläche
EINKAUF <Programm>
Physikalischer Effekt
Formale Sprache
p-V-Diagramm
Gesetz <Physik>
Quick-Sort
EINKAUF <Programm>
Computeranimation
Entscheidungstheorie
Homepage
Entscheidungstheorie
Homepage
Digitalsignal
Font
Formale Sprache
Digitalisierer
Kantenfärbung
Indexberechnung
Schnittstelle
Beobachtungsstudie
Softwaretest
EINKAUF <Programm>
p-V-Diagramm
Mailing-Liste
Bitrate
Computeranimation
Entscheidungstheorie
Rechenschieber
Digitalsignal
Formale Sprache
Minimum
Stützpunkt <Mathematik>
Wort <Informatik>
Twitter <Softwareplattform>
Digitale Photographie
Mustervergleich
Hypermedia
Randomisierung
Vorlesung/Konferenz
Twitter <Softwareplattform>
Bildgebendes Verfahren
Metropolitan area network
Soundverarbeitung
Arithmetischer Ausdruck
Mustersprache
Twitter <Softwareplattform>
Computeranimation
Entscheidungstheorie
Gasströmung
Web Site
Arithmetischer Ausdruck
Gruppenoperation
Gamecontroller
Inhalt <Mathematik>
Grundraum
Fokalpunkt
Computeranimation
Eins
Videokonferenz
Softwaretest
Nebenbedingung
Gebäude <Mathematik>
Magnetbandlaufwerk
Automatische Handlungsplanung
Familie <Mathematik>
Partielle Differentiation
EINKAUF <Programm>
Computeranimation
Videokonferenz
Entscheidungstheorie
Arithmetischer Ausdruck
Erwartungswert
Stichprobenumfang
Hypermedia
Mustersprache
Leistung <Physik>
Lipschitz-Bedingung
Subtraktion
Bit
Arithmetischer Ausdruck
Besprechung/Interview
Indexberechnung
Bitrate
Computeranimation
Videokonferenz
Leistung <Physik>
Prozess <Physik>
Orbit <Mathematik>
Vorzeichen <Mathematik>
Ereignishorizont
Computeranimation
Videokonferenz
Patch <Software>
Chirurgie <Mathematik>
Digitale Photographie
Reelle Zahl
Trennschärfe <Statistik>
Gruppe <Mathematik>
Authentifikation
Reelle Zahl
Grundraum
Bildgebendes Verfahren
Avatar <Informatik>
Web Site
Perspektive
Zahlenbereich
Vorlesung/Konferenz
Vorzeichen <Mathematik>
Bitrate
Computeranimation
Eins
Rückkopplung
Bit
Shape <Informatik>
Bildschirmmaske
Bereichsschätzung
Digitale Photographie
Statistische Hypothese
Bildgebendes Verfahren
Computeranimation
Videokonferenz
Videokonferenz
Arithmetischer Ausdruck
Bit
Digitale Photographie
Vorlesung/Konferenz
Inhalt <Mathematik>
Gerade
Computeranimation
Videokonferenz
Web Site
Arithmetischer Ausdruck
Gruppenoperation
Vorlesung/Konferenz
Computeranimation
Videokonferenz
Analysis
Schreib-Lese-Kopf
Neuronales Netz
Addition
Darstellung <Mathematik>
Web Site
Flächeninhalt
Freeware
Digitalisierer
Authentifikation
Profil <Aerodynamik>
Bildgebendes Verfahren
Computeranimation
Videokonferenz
Schreib-Lese-Kopf
Subtraktion
Web Site
Gruppenoperation
Inzidenzalgebra
Raum-Zeit
Computeranimation
Gruppenoperation
Richtung
Homepage
Mustersprache
Digitalisierer
Mustersprache
Mereologie
Stichprobenumfang
Richtung
Zeiger <Informatik>
Leistung <Physik>
Videospiel
Web Site
Prozess <Informatik>
Mustersprache
Gruppenoperation
Videospiel
Richtung
Hilfesystem
Computeranimation
Gruppenoperation
Videospiel
Web Site
Vorzeichen <Mathematik>
Gruppenoperation
Vorlesung/Konferenz
Computeranimation
Konvexe Hülle
Natürliche Zahl
Content <Internet>
Kommunikationsdesign
Quick-Sort
Computeranimation
Gruppenoperation
Mustersprache
Rechter Winkel
Einheit <Mathematik>
Mereologie
Minimum
Mustersprache
Inhalt <Mathematik>
Facebook
Gruppenoperation
Mobiles Internet
Formale Sprache
Verzweigendes Programm
Profil <Aerodynamik>
Newsletter
Kombinatorische Gruppentheorie
Physikalische Theorie
Quick-Sort
Computeranimation
Videokonferenz
Digitalsignal
Lesezeichen <Internet>
Twitter <Softwareplattform>
Mereologie
Ereignishorizont
Touchscreen
Druckertreiber
Graph
Vorzeichen <Mathematik>
Grundsätze ordnungsmäßiger Datenverarbeitung
Formale Sprache
Vorlesung/Konferenz
Information
Ereignishorizont
Elektronische Unterschrift
Computeranimation
Arithmetisches Mittel
Interpretierer
Arithmetischer Ausdruck
Vorzeichen <Mathematik>
Mereologie
Gruppenoperation
Formale Sprache
Formale Grammatik
Inhalt <Mathematik>
Computeranimation
Einheit <Mathematik>
Streuungsdiagramm
Computeranimation
Dichte <Physik>
Web Site
Gebäude <Mathematik>
Garbentheorie
Computeranimation
Energiedichte
Satellitensystem
Shape <Informatik>
Überschall
Bildschirmfenster
Zustand
Zellularer Automat
Faktor <Algebra>
Computer
Binder <Informatik>
Computeranimation
Perspektive
Gruppenoperation
Abstand
Computeranimation
Videospiel
Kreisfläche
Rechter Winkel
Flächentheorie
Systemzusammenbruch
Strömungsrichtung
Unrundheit
Computer
Datenfluss
Computeranimation
Touchscreen
Tabelle <Informatik>
Streaming <Kommunikationstechnik>
Shape <Informatik>
Webforum
Bildschirmfenster
Vorlesung/Konferenz
Computeranimation
Schreib-Lese-Kopf
Hypermedia
Besprechung/Interview
Computeranimation

Metadaten

Formale Metadaten

Titel Possibilities for using speech and gesture recognition for the future of mobility
Serientitel re:publica 2015
Teil 131
Anzahl der Teile 177
Autor Wex, Philipp
Edwards, Vanessa van
Schäfer, Mathias
Lizenz CC-Namensnennung - Weitergabe unter gleichen Bedingungen 3.0 Deutschland:
Sie dürfen das Werk bzw. den Inhalt zu jedem legalen Zweck nutzen, verändern und in unveränderter oder veränderter Form vervielfältigen, verbreiten und öffentlich zugänglich machen, sofern Sie den Namen des Autors/Rechteinhabers in der von ihm festgelegten Weise nennen und das Werk bzw. diesen Inhalt auch in veränderter Form nur unter den Bedingungen dieser Lizenz weitergeben.
DOI 10.5446/31914
Herausgeber re:publica
Erscheinungsjahr 2015
Sprache Englisch
Produktionsort Berlin

Inhaltliche Metadaten

Fachgebiet Informatik
Abstract Speech and Gestures are guiding our way into the future of mobility and play an important role in our daily lives and the way we get along. This session will provide insights on how speech and gestures impact the way we communicate and interact with each other as well as with our surroundings and also proves how powerful gestures can be for expressing ourselves.

Ähnliche Filme

Loading...