 monitor 2 alpha Bravo change rate change didn't recognize it won't flash okay so the winks I know that it took the change rate down change rate change rate stop and mark this are you probably marking us but I'm gonna mark some of the ones that I think I'm having trouble with if we agree go zoom in change rate right stop I think I would cycle a whole thing one more time monitor one monitor one monitor to monitor to voice command standby activate activate go go go left left right stop change rate change rate easy easy still cameras still cameras or too much too much change rate change rate tilt up zoom in tilt up stop focus far stop mode active select one time particularly the mode activity is on the standout it is off so that means you've activated right so we knew that and you already knew that so if we I'll talk to chef how we're going to manage that okay well like I told chef what's most important our most important feedback is your opinion sure that is our most important feedback so you come back happy whatever makes you happy okay this would be where you deactivated if you wanted to for as required that's better yeah yeah with the data is compared against ground data that we acquired during astronaut training hopefully we'll be able to see or the effects the space environment has on the speech process and voice recognition there are several successful applications of voice commanding systems in in the commercial sector for example in the area of aid to the handicap and handicap person can control by voice a motorized wheelchair medical reporting currently doctors are using voice recognition to to generate medical reports whereby they're looking at a x-ray for example and are examining it and are inputting words into the recognizer that it recognizes and it's generating report about the doctor's examination other applications is access control where they use a speaker verification system is the person that wants to get into this door truly the person it is and they use a specific voice print algorithm to try and determine if this person is indeed the person he says he is the system that we use is what they call speaker dependent system which means that the crew each crew person has to train the system before it can use it training consists of going through a vocabulary two times and saying each word each word is then digitized and stored in memory as a template or voice print similar to a person's thumbprint and then all those words are then saved according to each person as their templates okay when the astronaut wants to use the system he will come in he'll plug in his headset and plug in the display in the shorting plug and then all he has to do is turn on the power switch to you on and that's the only manual step necessary after when the system powers up then the system automatically prompts the astronaut to say his name when he says his name and recognizes who he is will go out and load his templates from memory into the recognizer then when he wants to control the system he'll say a command it takes that word and digitizes it and compares it with the words that were loaded into the recognizer if it finds a match it sends that in for it sends some information from the recognizer to our controlling hardware where we process information figure out what word it was and then send the appropriate signal out to the cctv system to control a camera or a movement or a monitor whatever the function happens to be the voice command system is the first experiment to be flown in space which uses voice is the control we think this is going to be useful to the astronauts for two reasons and the first reason is that by having a system which is voice controlled the astronauts hands and eyes are free to perform other tasks the second reason is that by using a voice controlled system it isn't necessary for you to be in the location where the system is in order to control it so you're free to move around and you can be remotely located no we can have as many people as want to can use our system we have it set up so that only five five people can actually have their voices put on to e-square prompts but we also have the ability to retrain templates real time so anybody who wants to use the system may not already have theirs templates made but they can come up to the system and make their templates anytime they want so we're not limited on the number of people who can use the system all right well we have 40 commands that are possible on the voice command system most of these commands are exact duplicates to what are on a cctv manual switch panel and these are selecting monitors cameras and working the camera motions like panning and tilting zooming focusing all of those we also have some bcs unique commands which are used to activate the system deactivate the system identify the user and we also have some special macro commands for example we have a command that will stow all of the cameras in the payload bay into the position that they have to be in for launch and entry simply by saying stow cameras so we also have some special features that the manual switch panel doesn't have well the way we chose the words to use is because they're the words that are actually on the switch panel so they're the ones they're familiar with when they think of moving a camera up they think of tilting it up so we we selected all of those words now they did tailor their vocabulary to their personal use words that they were the most comfortable with words that work the best for them so both of our astronauts have have a different vocabulary but they're also very similar and they're the words that make sense to them and that's how we came up with our vocabulary well there's not a lot known about the effects of microgravity on the voice we do know that in zero gravity that the position and the shape of the lungs and diaphragm are altered now if this causes a great enough distortion in the voice good recognition could be difficult to get so we're expecting that this may be a problem well what we're going to do is that if the astronauts do find that they have trouble getting recognition we have the ability to remake their templates real time so simply by clicking this mode switch twice the system is automatically put into the template making mode and our system will prompt them through the entire vocabulary list they'll say each word twice and they'll have a brand new set of templates that are real and representative of their voice at that time it feels so fabulous you know there's times when you really think it isn't going to fly it's just it's not going to go and now not only is it going to go but our astronauts love it they love it they're having fun with it everybody we've shown it to likes it people are coming up out of the corners with ideas of how to use it and it really makes you feel like you've accomplished a lot