competence to even if they have little in common with the speakers, actual personality. with beyond words, a voice also transports motions and can even bring things to life. puppets become real because we relate to like other human beings. so used to put more a city it illustrates how we instinctively relate to a human personality, if it has a voice. so co operative mammal on it, and we're on a puppet, for example. and because of changing body cues and changing vocal cues, that the perception of the emotion, the perception of, ah, the person's or the, the puppets intentions are chance. oh yes. let me in the eyes just a little bit generous. t sympathetic. even,

you know how brains create real people from the voices they hear. even when the people aren't real sick, if you didn't, once you give a machine a voice, it gets a personality as if it were human, much inconsistent. it's an automatic reflex, issamottom ethic. there will shasky mult good decal done in war, and research shows that people's feelings change if their computer car or coffee machine has a voice in who the company to said, well, the vocal acoustics we give machines, could even determine how we interact with them. it did tell me not to dilemma neil boys yema voltaggio, the clinician for her wake up. wake up. how can i help you? what can you do? you can, for example, asked me to introduce myself for the chat a little. can you introduce yourself? i'm a firm at robot, a social robot bill to interact with people in the same way you interact with each

other. so i can smile and nod. gabriel's cancer is one of the creative dispersion process. top of the robot was launched in 2011. i looked a bit more crude back then with cable sticking out from my head. they came up with the idea to cover the cables with a fur hat. and that ladies and gentlemen is where the name for hack comes from. i don't really need my for had anymore. i look pretty as i am. don't you think? i don't know what the original interest comes from really. i think it's a very fascinating idea of creating and, and now an agent that interacts like a human and it behaves like a human. it's fascinating by its own right. but it's also again back to the idea that if we can do that, we start to get the better understanding of how we as humans work in the future. gabriel's cancer wants for her to behave like a human during

a conversation. but as soon as scientists try to transfer our human behavior to machines, it quickly becomes apparent how complex or behaviors are. but i'm originally from you like being on today for how it's supposed to make small talk. the robot searches the way on his own for responses. what did you, what do you mean by that? and you are quite stupid. ruth, is this a for? so i have no idea what the robert would say next. so it's, it's, it's a surprise for me. what it says, and it's a bit fascinating to see how the conversation on post ah, although the conversation takes on expected turns. her head has already mustered the basics when to speak, and where the conversation partner is looking and how much i contact is appropriate

from the scientists to program. so with a whole range of emotional facial cues. however, the find a difference is we express using mimic and our voices are proving trickier. so as humans, for example, we have this micro expressions. so my eyes move a little bit all the time. i make small movements with my face, and we want the robot to have those small movements old, so otherwise it looks very robotic and not very human like. so we think that the face is extremely important and the way we give feedback to each other and everything is expressed through the face. but also through the voice and, and the way the tone of our voice and so on. that's why it's so difficult for 1st to react appropriately. the same word, the same sentence can come across very differently depending on the mood, the occasion or the person we're talking to. unfortunately, there's no use manual for humans that fur hat can learn from yet. anyway,

there's plenty of cases where, you know, a face can be identical and the same features, but the context, the body and the voice dramatically changes how we understand that person. there's all sorts of different kinds of cues. in terms of intonation, pitch, contour, or format, characteristics that change how we perceive other people's voices, the emotions that they're feeling, their intentions. how do we read moods? mark shreds is researching how tiny movements in our facial muscles can influence our communication with. ready the eyebrows, cheeks, lips, and chin all contribute to forming very different types of smiles with face subtle because it has to do with micro expressions that you see around the i region

or the mouth region. or you can fake a smile. like if i, if i do this in a very fake manner, you can see that the birth is pretending to be happy or being cynical or sarcastic, but it's not revealing what, what, what his or her true sentiments or emotions are. and it's not only smiling, it's so also in the, in the very subtle movement of eyebrows. the very subtle movement of blinking a recent u. s. t. v shows focused on body language. lightman was the protagonist of the crime shows lie to me. he was an expert in micro expressions who believed facial expressions could expose lies and suppressed emotions. huge shame and shame, contempt. these expressions universe can we really identify

every single emotion just by practicing some scientists think. so apparently, all we need to do is consciously notice each millisecond long facial expression. the results are used in market research to find out which commercials and most effective, especially trained security teams at airports. also analyzed facial cues for potential terrorists you will be really that easy to tell when criminals align spending. hollywood wants us to think so. 43 muscles combines produced possibility of 10000 expressions. now, learn them all. you know, polygraph how much that we spend on this damn project, but the scientific world takes a slightly dim feet in real life. it's often much harder to do. so for instance, our displays that from your micro expressions, you can see whether someone is flying or not. but that's close to impossible. so

for most kinds of people lie about something. if you're close to chance level, about guessing whether or not someone is speaking the truth or not. ironically speaking, if your life becomes more important, like if i'm lying about something which is which reading metrics like i have to hide something it's called the pink elephant effect. your cues to lie become more, become clear for the other person. so the more you try your best, not to show that you're lying. the more likely it is that people will see that your life. how easy is it to tell when someone is lying? mark's face is looking to children, aged 5 and over for the and so yeah. the children are asked to tell the prince in a computer game. the truth of the open from the act remove that lie to the dragon.

mouse in the door. this supposed to help the prince hide from the dragon, cameras and microphones, records the children's behavior in an attempt to find any differences in the back. after recording numerous children, the results highlight signs the point to line. i think that there is a lot more you don't do to do that. it's not when you look at the faith in when they're being truthful, they are very open and they just kind of expression when they're being when they're lying and they have depression that they're being watched and being observed. you see that they have this sense of, i'm being observed and you can tell from facial expressions around the mouth area, which is both more marked, more mark kind of expression than in the truthful condition. it's something about the voice. so when being truthful, they have a very soft mobile,

warm voice from the line. they tend to be a little bit more using creepy for it's like talking a little bit like this. but not every child showed the same cues. so it's not a reliable way to tell if they are telling the truth or not know that the generally were much better at controlling our facial cues than our vocal cues. every we produce is created by over a 100 muscles all working closely together with emotions, all to muscular tension which impacts the tone of our voices. i. everything is controlled quite different parts of the brain. with the muscles in the chest and

abdomen that create the required air pressure muscles in the tongue, lips and face that vary the voice. and of course the larynx and vocal chords. the high, the pitch. when we become excited, for example, the faster they vibrate, does everyone hear the same thing? when a stranger talks to us, to we all come to the same conclusion in deciding if someone is trustworthy, extraverted or willing to try new things? parent schuler is conducting research using a range of different voices group. although the group doesn't agree on everything, the data shows some clear tendencies. artificial intelligence is being used to help identify them. from if my mom's mind at ease of my theory is that if a human can hear something or

a computer can pick up on it to own go thought divert order. but it becomes a little spooky in i, when we got beyond what a human can spawn alice can connect them in from one another. who on printer to so we're now trying to assess whether speaker has cove at 19 on our special hot class for yes or and minus for now we're damaged minos covered northern 3, the nora lyndon. so no good. i've got one vote for positive. suddenly it was negative. the come to me is the next voice at her eyes. this northville runner. i'm in the delay. we now have 3 positives and one negative doctor. i'm going to say positive it was it maurice newbies. yes, that's right, diagnosing covered by simply listening to someone's voice, sounds risky, at least when we rely on the human ear. at the start of the pandemic, we on shuler programmed a range of voices into artificial intelligence is a more accurate diagnosis now possible. drew on it to me, this is the

a symptomatic negative cases, negative, hain underwritten. so the loss is the symptomatic positive k e in one of those one of here to most little so the oceans eats and his elbow turner is . and here's the hours complete cloud for we can see quite clearly on the right of the upper tire in stock for washington. as host the signals are, there are lots more signals we can use to regarding like the uncontrolled vibration of the vocal chords that leads to irregularities and the stimuli, and as of a certain throat in us, somebody. breathlessness is out of the cause. as long as speech breaks written due to one of the mythic arden and the analog woman up close music and logan fuel tis at all we kite could so often the signaling of his passport and sadness wound upon the thing. the computer enough examples to reach a decision,

the computer and differentiate between asked man, or a call and entitled person candidate or to us ma, occurred on an upcoming dentist at least 85 percent of the diagnoses made by artificial intelligence were correct. what's more, computers can also identify a d, h, d, parkinson's, house farmers and depression by analyzing the voices. anything that goes wrong in the body or brain impacts our voices. to make a diagnosis, official intelligence looks at up to 6000 different vocal cues. the new technology could allow diagnoses to be made more easily and early on. every word we say reveals more about us the livery lies. and as listeners, we are influenced by the person speaking to us. subconsciously we relate the person

speaking. we internalize their anxiety, uncertainty, excitements, or happiness as if it were our it's attract, the synchronization connects to people through mimicry. in general, mimicry is something that we do a lot in normal kind of conversations. and it's reflected in various aspects of our communication from the words we use the syntax, we use the property, we produce the in the nation and the temple, but also the non pro, the communication for instance, smiling behavior close to the relationship or desire for relationship. the more intensive subconscious mimicry to come. we also mimick more strongly when we want to be like smile. is it clear?

signal, dismounted person figure somebody often does something of happiness in yourself. like if you, if you see a smiling person, you sometimes start to smile yourself. and so i don't know, maybe one of the attractive feature of the mona lisa. exactly, to do with that. like there's something intriguing, something attractive about looking at the painting because she elizabeth smiled. she elicits happiness. we allow ourselves to be influenced by some one else, is mood. march 5th, wanted to take a closer look. in this experiment, the speaker is describing something to her audience. her manner is animated and she smiles frequently. oh, oh, no little place here. audience reacts similarly, they smile back, not in agreement and give positive feedback. oh yeah, i was it, andy. but what happens when the same speaker repeats the process,

the more seriously her listeners also look more earnest. i appear to concentrate more and the reactions are more constrained. synchronization signals, empathy, an interest in the other person. how communication is successful, we tune into the more closely and it's not just our facial cues that sink. it's our voice. it's to try to express an emotion vocally that we're not feeling is nearly impossible. so what transforms a voice into an instrument that can appeal to persuade or motivate other people and with all of a needle has carried out numerous case studies and all have the same outcome. it's not what we say that counts. it's how we say it

and stim, it's an old lovely voice is an extremely complex, multi layered signal it on the bus was. evans will have information that we want to impart only to that, absorbing it to hard work from a cognitive point of view and strength. and so we need to work on how it presented his eyes, or emphasizing words can send a clear signal indicating which part the conversation or importance conduct need to consider short pauses to versus this dish versus own business. in fact, are people who communicate like this are regarded as more likable. done is more business eog mod. oh, that's it with. so it's all about how we use our voices to package the content that, you know, one of the fun edition is performing a short test tracking of how well can his coworker presented text his reading from for the 1st time we're servers. as soon as the user is back, artificial intelligence is again used for analysis. the computer calculates

a score of 47.7. it splits the voice into 16 parameters, including speed, rhythm, melody, volume, and pauses. a score between one and a 100 for acoustic appeal is then calculated out years prefer a varied pitch, usually around 2 octaves. charismatic speakers often switch between loud and quiet, fast and slow. the ad the loves the makes, the voice sambal melodic and their standards of dimes. and the bush of the money to century is principal has been used by populists and demagogues to capture the attention of audiences. because even ancient civilizations understood that the only way to motivate and inspire people was to get them to listen, don't to public speaking, projecting and modulating your voice to achieve the best result was taught in

classic antiquity. now it's become of loss of skill. it is and also in the monkey sample builder as a dust muslim. additionally, but i'm, it's possible to train your voice to transport information effectively because of what shots blouse, no difference to learning a new vocabulary. gramma, dimmer ions whose edson landon pies off his green, all of the neighbor, has developed a computer training program after 5 seconds. so they know that you have the pitch range that you the principal is fairly basic, right. the upper and lower lines showed the pitch when you're circles and different colors in size represent speed volume and pauses. ling to different. ah, yeah. what i really like to do is to try different food from different countries. and yeah, i really like spicy food also uses a showing what they can improve in real time in the golden time or meanings. in the extra one day of training, the speaker tries again good chances to win. and patrick errors by 90 percent

saving band at school is 12 points higher than the previous day. how does your company handle the main improvements are in pitch variation clients the honda pump, his score has sword from 34.5 to 73.3. that's almost doubled his previous attempt of put up a long contin months on this app has not only it's a clear improvement time card process for remote employee, other voices a so seductive that we can lose ourselves in them. a check as shown in this experiment with some drivers were given instructions by this voice leading to the asking fellow with like, wellness, nita and others by this slightly less engaging voice. closing this to us, and i was informed that nita lassie of a nice vlosky ist, and that's of the what the drivers didn't know was that half way through the

experiment. the sat and i've started giving incorrect directions. i've shown facia when they got progressively worse and he was breaking the pope and we wanted to see at what point the drivers would quit safely. citing us by the us. we were able to show that the more expressive, the more convincing voice kept drivers following the wrong route for longer as thought of the problem might have going against their better judging. luton advised them conflicts and when soon garcia i and we had to call them and explain it was just to test and ask them to come back, isn't fighting and vice longer folks and will not have your annual from western song, saudi quality to lucas by the one test, an engaging voice plays a key role when it comes to flirting or meeting a romantic partner. hello. hello, i'm village in hilton willie will. i'm caught you now doula. oh, so i'm looking for a woman for the long term. i'm who's attractive was 1st, who do we desire? every red us, we make snap judgements when it comes to one of life's most important decisions

quickly and irrationally. it's ab judgements are, have always thought they're really fascinating. it's sort of how we determined who we want to date, who we want to be friends with, or we don't want to be friends with. and we don't have a lot of introspective acts as to those feelings. we're drives that we usually encounter people. and we like them or we don't like them and we have a good sense of that. we get along with them. and these things determine all of our behavior. are we all born with the universal cult? is it nature or nurture that allows us to interpret character traits and read emotions through facial and vocal cues? one thing is, certain, we react to these cues from a very young age, or we are just like our animal ancestors. i mean,

obviously primates never developed verbal language like humans just like us. they communicate vocally and they know how to interpret the signals. just as sheila prepared the shall fall, scuse, that's designed to sub i always assumed that there were huge differences between verbal humans and non verbal primate looking. but research shows that the auditory cortex in both species is more similar than expected. if it goes with a verbal or non verbal, it makes no difference on how the brain processes signal skill login is su, gitmo level lou mascot, the law has tested humans and primates using functional magnetic resonance imaging or f m r i book the results show that both groups react to their own species, voice in the same parts of the brain. ready listen and we,

i'll ancestors also probably use these areas $20000000.00 jessica primates process . vocal cues the same way we did, even without language it. oh yes, no, she did do the brains architectural change slightly and humans to process language and that's the coolest picking it brought up a whole miss it in, but the mechanisms have stayed the same in other species for anything beyond language. we can either entity emotions, personality is latesha, vic in only multiple dismiss research into how primates interpret facial cues shows similar results. again, similar brain structures to humans are activated in the primates. does that mean that we are born with the ability to understand facial and vocal cues? lou,

yours is 10 months old and is getting ready for an experiment. siri, yes. and was to measure yours, his brain waves to see how he reacts to unfamiliar faces. and he already judge who's trustworthy and untrustworthy. and then i was to leave him after how many we carried out research where we showed babies a range of faces for 50 milliseconds. that's only a 20th of a 2nd one. it's so quick. we assumed that babies wouldn't even registered the faces i taught since in however, we identified activity in the brain that prove the babies had not only registered the faces, but had even made the decision about whether they were trustworthy or not. but is it night or learned? ah, the video, nice stuff and all skin of anger ball. we don't believe that

a baby is born with the ability to judge whether face is trustworthy or not. and then it's more likely to be a combination of learning processes and, and inherent or early interest and pieces. and one of the rooms, because i'm interested in going to over the 1st few months, faces and voices are a baby's most important learning resources. parents intuitively use pronounced facial cues, emphasize sit and words and exaggerate. this captures the baby's attention and allows them to recognize emotions more easily. by 6 months babies can already differentiate between happiness, fear, sadness, and anger. you want to play, i see. i'm still a bit sleepy, just like a child fur had his learning to understand it better and practicing how to behave

in a conversation. he analyzes the movements and eyes if his conversation partner using a camera. my name is gabriel, for it has to know whether i am talking to perhaps, or my colleague here. and so, and that's quite tricky. and we call that a multi part interaction. we are more than 2 people talking. and one of the ways of handling this is that we track the head post of the users. and so here we can see that the camera has detected as to here and can also recognize our faces. so if i turn around, look back, it will see that i am the same person still. it's time to play a game with fur hat gabriel. my detain takes turns, drawing a shape. while the other players guess what it is? could it be star? no. is it a flower? yeah, it's a power. got it. so my guess and further. now make

her were i know peter snake this. yes. this is a good one. for both he gets or is it about? her hat will look and sound more like a human over time. but he won't be identical. study shay, we prefer a clear distinction between humans and robots. oh, we find it too creepy. the boundaries are already blurred in the media. after 40 years apa is back on stage. but in real life course, but as advertised, it's light time is simply passed the group. it's 70 year olds by only their voices, a still real exposed. we're at the start of a huge technological shift towards this. your technology,

we are often asked to record actors, voices, is act of don't just it is act ultima. i predict that over the next few years, these real life voice recordings will become superfluous socially to bump it. it'll kick isn't it? because we'll be able to create a new synthetic weiss's using his scientific principles. would you love it was issued the possibility i don't know what you're talking about. how do i know that you and frank were planning to disconnect me? and i'm afraid that something i cannot allow to happen, artificial intelligence making independent to see since we're still a pipe dream interact, stanley kubrick's day to day we live with it may be that's a good thing because i, i doesn't make emotional decisions or to come to luring voices, it's neutral, and impartial, and everything. when not, bryan you program in a i,

if they see that, you know, african american is linked with hostility and crime in media depictions in t v. and those are inputs into the i, the a i is going to pick up on that and act accordingly. you'll be shown a series of if so i is more like up the move realize that enlighten me was shown how some faces are automatically linked to stereotypes. but it goes up to we're testing for racial bias, the races. they're all races. yeah. 80 percent of people who take this test are biased. we're just looking for the guy and science dictates the subconscious bias directly impacts opposition verification time for each of them. they leave a lot of collateral damage in the brain, right? it's not just a stereotype living in sort of a filing cabinet in the brain, right? they're changing, approach and avoidance tendencies, behavioral tendencies, motor tendencies, visual tendencies, auditory tendencies. john freeman is looking at exactly what happens using f. m r i

. the test could be shown several different faces, as well as the part of the brain responsible for facial recognition. other areas that process, social and emotional information are also activated. these areas memorize bias and personality traits. to provide a rapid response, our brains make fast prediction. we register what we perceive to be most probable this can often be adaptive, right? if you walk into a restaurant, you expect to see chairs and tables and a waiter, etc. you're not gonna waste a lot of metabolic resources. the brain time, the visual systems, resources and processing every single object in that space. you would generate a bunch of hypotheses, you know what a restaurant is, and you kind of run with those hypotheses. and you don't, you use expectations to fill in the gaps of the brain is too lazy to figure out

itself and does want to re weigh some resources on so are we merely at the mercy of these mechanisms? john framing refuses to accept this theory. he's carrying out research to find out how we learn the stereotypes and whether we can and learn them. he shows the test script range of faces linked to specific character traits. so given all that, we wanted to explore our capacity to rapidly acquire completely novel facial stereotypes out of thin air. he bull that have a wide cell in width, which is the nose bridge on the face. and it's a queue that really has nothing to do with anything interesting. it's just simply the how wide the bridge of the nose is. so it's an arbitrary facial feature and 80 percent of the time we're pairing this wide fell in with trustworthy behaviors. so

now they see completely new faces, not the ones that they had previously learned about, and that have wide and narrow saelens, that arbitrary facial feature. and indeed, what we found was that on a variety of different measures, more conscious, less conscious that people are applying these stereotypes. they are automatically activating the stereotypes without their conscious awareness, from just a couple of minutes of learning in our brains, a highly flexible when it comes to stereotyping. we can learn to evaluate faces differently, at least over the short term. john now looking into a training method that works long term. the same principle applies to voices. ultimately, the more we know about these mechanisms, the less susceptible we are to being deceived by 1st impressions, a simple meals and pursue 1st impressions. fascinating, sometimes deceptive,

but always a special even magical moment and may be the start of a new relationship will be discovered so much more than will be sore at 1st sight. ah ah ah, a beginning of a story that moves us and takes us along for the ride. it's all about perspective. culture

information this is dw d w made from mines. oh mm hm. and what's behind d, w? news? africa. they show the issues shaping the continents. life is slowly getting back to normally on the street to give you enough reports on the inside our correspondence with on the ground.