0:00:02good morning this is joe campbell from mit lincoln laboratory
0:00:06and i'm joining by tell me canyon in from university of eastern finland
0:00:12were here this morning with a set of distinguished panelists
0:00:18to honour and represent and reflect on our dear friend i jack godfrey who passed
0:00:26away last one
0:00:29we have a very full agenda today so
0:00:34i think what will i wanna just remind to remind you of a couple things
0:00:41there were manning many people wanted to enjoying the panel but on the virtual stage
0:00:48door only room for six
0:00:50so if you could send messages in the chat
0:00:55we will be happy to share them with the godfrey family as a memento from
0:01:01this event
0:01:03now let me handed over to tell me
0:01:07totally that's a moment of silence
0:01:11okay so probable system also might be so we will go moment was on as
0:01:18norm so
0:01:20based on
0:01:55okay the criminals
0:01:59so i think you know angel
0:02:02thank you if i can have the next slide please
0:02:11doctor john j godfrey led a very distinguished career
0:02:16main so many friend friends along the way
0:02:19and is a pillar of our community
0:02:23he is largely the reason why this workshop exist
0:02:28through is
0:02:29efforts in leading corpus space research
0:02:34is you know phd from georgetown in linguistics
0:02:39his early career work focused on psycholinguistics at wright patterson air force base that the
0:02:46air force research laboratory
0:02:48and the university of texas at dallas is collier centre that some of the earliest
0:02:55papers in human speaker recognition where published by jack in those days
0:03:03he was a contributor to the revolutionary speak and spell troika texas instruments
0:03:11this was
0:03:13the first that i know of spelling computer for children very effective
0:03:19is served as the first executive director of the linguistic data consortium
0:03:26this enabled him to drive a whole corpus based already community
0:03:33back any all day is
0:03:36people will publish results and whatever datasets they would collect
0:03:41usually ad hoc
0:03:44without rigour in it was impossible for people to compare performance across systems
0:03:51so this was a big contribution
0:03:54as the chief of the h l t group it and the say you provided
0:03:59national direction in litres and brought together this international community promoting an evaluation culture as
0:04:07whereabout to see in a few minutes
0:04:10is a dedicated has been father friend mentor
0:04:14and loves to fish and hold great stories we learn a lesson
0:04:20i just have another minute or so the
0:04:26but what i'll do you now is let tony at a few remarks as the
0:04:31is gonna s p l c signature
0:04:35thank you so his or her or something the special interest group of a speaker
0:04:40role recognition community and so we are going to some this is the remainder of
0:04:47this on is a common is able to so are you over to work well
0:04:54really wanting to introduce bills
0:04:58with control
0:05:01thank you tell me
0:05:04i'll just quickly say the that's jack with his wife nina the aim at wright
0:05:10patterson air force base
0:05:12he loved to fish
0:05:15that was is real big thing and then where we've got a huge smile there
0:05:20is a holding my bell i'm two hundred centimetres tall so he was upon is
0:05:27tells for that great picture
0:05:31now i'd like to introduce a movie where jack will be able to tell us
0:05:36in its own words
0:05:38the importance of evaluation and the scientific method and its quest for understanding
0:05:46this is courtesy of the johns hopkins university c lsp animal lecture he gave in
0:05:53two thousand twelve
0:05:56but i have the video please
0:06:47it is
0:08:43it is
0:08:46once i models
0:09:02it is
0:09:19this is
0:10:22for so
0:11:13so problem
0:13:15so it is
0:14:49that was
0:16:27more than
0:16:52why the
0:16:56the only ones
0:17:27seven video really captures the essence of jack godfrey is methods in driving an international
0:17:36research community
0:17:39finding results there are surprises and wanting to understand why
0:17:45and this was a key the johns six jack godfrey six s
0:17:50and largely to our community six s
0:17:54those evaluation curves over the years
0:17:58showing performance the problem getting harder making performance gains again changing the problem to make
0:18:07an even more realistic was this of virtuous cycle
0:18:11the jack brought to the government and in the us
0:18:17and also internationally and help the number of government partners and research t means
0:18:24there was instrumental in the advancement of or feel
0:18:29the things that have been made by the community here at odyssey over the last
0:18:34two decades have been remarkable and i congratulate you offer that and we can think
0:18:40jack for supporting of the datasets to drive all this and is this insistence and
0:18:49now will transition into the upper panel session
0:18:54we have sticks distinguished colleagues in dear friends joining us
0:19:02and the first one is craig greenberg
0:19:06he was actually in that video with jack that you just a the whole video
0:19:11is over an hour but we didn't have time to play the whole thing
0:19:15so let me handed over to craig take the of a few minutes four minutes
0:19:22worth the of remarks or show a slight evaluations
0:19:30and it was a degree privilege and you're to get to know and we're project
0:19:35jack was instrumental in having various human language technology evaluations of news
0:19:40including of automatic speech recognition spoken dialog systems
0:19:45and of course of speaker and language recognition evaluations the median and ninety six and
0:19:50can do you want to their
0:19:52definitely involved in the nist evaluations offering his vision an insight sometimes aligner french
0:19:59and all along with a joke in a kind word
0:20:02and resulted in two thousand and i started working the nist on the speaker and
0:20:07language recognition evaluations which we typically referred to as sre and lre
0:20:12actually all the direction of all aspects of the sre use another use
0:20:17in the beginning evaluation training data collection is all the weighted including workshop
0:20:23there is a leadership dedication
0:20:25generate householder real of the sre series and the first evaluation with ten or so
0:20:30systems and around four thousand trials
0:20:33into a series that commonly includes hundreds of systems could be millions of miles
0:20:38the other easy reason to and similar groups that are is all sources
0:20:43i understand the timit corpus the jet worked on was originally set around one male
0:20:48and one t
0:20:49before he retired we began running evaluations entirely online
0:20:54surely this tremendous contributions and it was remarkable progress of the evaluations and the technology
0:20:59and so
0:21:01part of whitney objects contribution was brilliance as a linguist
0:21:06just to give a sense is
0:21:07sometimes i feel f voicemail he'd come in here office and right on your whiteboard
0:21:12the phonetic transcription of your message
0:21:14where we used that's what i was told by some of those of her colleagues
0:21:18personally i really think of and all that if you didn't answer
0:21:21i didn't that didn't get to see the sort of thing lyman action
0:21:26they're in one been you notice my use of the non-lexical conversation also
0:21:32the sound was a
0:21:34we just found that using able to correctly infer that i was the simpsons fan
0:21:40i'll i'm not sure of me is that only we also really like the simpsons
0:21:46i'm so grateful that in addition to working with great i got a known person
0:21:50we don't think what we were years after evaluation maybe millions and at conferences
0:21:55where of course we talk about language and language technology
0:21:59but also politics history philosophy economics education
0:22:03just to name a few topics about which is usually knowledgeable
0:22:07another so much
0:22:10you reminded me not only professional managers but also personal items that will continue to
0:22:14carry with me all my
0:22:16and so like to take this opportunity to take two injectors mentor shipping guidance as
0:22:22well as for is tremendous contributions the human language technologies
0:22:25and to the nist evaluations
0:22:28after such monumental where
0:22:29i don't we all agree that he rest in peace
0:22:36thank you craig that was very nice
0:22:41next we have douglas reynolds
0:22:46is an assignment in the us government and the is in my
0:22:54don't can i join us in person but he kindly sent this video the we
0:23:00will play now
0:23:08recording could happen or weekly where p e
0:23:12three would like to select keywords and i'm your friend happy jack godfrey
0:23:18but my earliest recollections of jack
0:23:20with the precursor to this whole odyssey workshop series ninety nine core margin use what's
0:23:27is relatively not you researcher having some of the jack stature come to my coaster
0:23:32listen to my work asking questions make me feel that what i was doing with
0:23:37the most important thing but the major motivator might really career
0:23:41but jack kind of way of doing that with whomever speaking with
0:23:44you matrix will since they were the most important thing but is warm apple nature
0:23:51one of jack's
0:23:52legacies to the speech community is being a high here in strong component of common
0:23:57corpus evaluation driven research and development
0:24:01in today's your numbers benchmark datasets and challenges
0:24:06it's harder to imagine a time when even small data sets were expensive and harder
0:24:11to manipulate
0:24:13and there were numerous speakers were published and cried datasets using a tricks
0:24:19and tracking enough everybody had about a hundred percent accuracy
0:24:24this around the mid nineteen edus the darpa was one of the first organisations to
0:24:28really push common corpus evaluations so the technical progress could be meaningfully measure
0:24:35jack along with this texas instrument colleagues which is george doddington you can strong advocates
0:24:40of the value of common corpora evaluations
0:24:44jack was instrumental in recreation in collection of the first conversational telephone corpus
0:24:50call switchboard
0:24:52but in a standard is pretty small twenty five hundred conversations with five hundred speakers
0:24:56but the time it was one of the data is that really started should drive
0:25:01the fundamentals in speech recognition and speaker recognition
0:25:09jack and became the first executive director and linguistic data consortium
0:25:14where you continued his dry to have a common corpora for human language technology tasks
0:25:20in expanded their catalogue with numerous amounts of
0:25:24novel weighting the collecting speech corpora including text into that mix and other types of
0:25:30data sets
0:25:32after ldc
0:25:34jack went on to become the each individual t research the dod
0:25:39here you continue to abdicate can drive you called virtuous circle research development that allowed
0:25:46him to leverage the worldwide research community
0:25:50but each antony open speaker and language recognition evaluations run by nist
0:25:55these evaluations have been
0:25:58the driver from much of the core technology that we'll be hearing about obviously this
0:26:04jack was always a fierce contractor the people in his great wherever you worked and
0:26:09not much one to deal with bureaucracy very well
0:26:12in fact idiot is good at here is always the skunk at the garden already
0:26:15saying we need to be standard and not trying to put on the niceties pursuit
0:26:22in addition
0:26:24jack's professional accomplishments he was also warm
0:26:29affable charming mare
0:26:31and i wonder person around
0:26:35in the problem family man friend mentor in a heck of a storyteller
0:26:41is it your soul this greatly by discriminately and based family
0:26:46thank you joe
0:26:53thank you do that was really nice integrity is one of the words the
0:27:01there really stands out
0:27:05so yes i want to introduce john for us all born this
0:27:11to speak about jack's work mostly in their intersection in the world of four and
0:27:20and then all hand over the introduction of the following speakers to tell me
0:27:26john first law
0:27:29and stroll
0:27:31good use and my slide or died we
0:27:36if you can do it that would be great
0:27:39in less they have them at the odyssey team
0:27:45there's actually go have your slides
0:27:49you go is it possible
0:27:51okay sure
0:28:07we next
0:28:19well i i'm very are known to be here and to say some walls of
0:28:24but to dye my story reading
0:28:28be began to be in a nineteen and ninety eight even if i saw him
0:28:32in matching you for years a the before
0:28:36nineteen eighty eight that was my first time in the usa
0:28:39my first time in the nist
0:28:42it's very
0:28:44the first five actually
0:28:46trying to do speaker verification and more exactly the first time i
0:28:52the idea of the evaluation with this war
0:28:58and from my own to go to public
0:29:02a common the vocal
0:29:05to be able to
0:29:07and the wheel beginning my first the discussion we draw
0:29:13where was
0:29:15very successful for you to my
0:29:18english ability to two hundred and speakers it possible to and it can also but
0:29:27also i will the dark object that and
0:29:32a little bit rate and very great by both
0:29:37was already a big i in the community and also by be context
0:29:43it was not at all
0:29:48the for this for during this first the meeting i
0:29:53have a strong memories about discussion within a but what means that you identification and
0:29:59that i and
0:30:02i have in mind if i but i agree on the table problem of via
0:30:07a cost to
0:30:08no one runs we can try to say what is happening you in france at
0:30:14this moment
0:30:16and a duck
0:30:18this then to us
0:30:20not only but refundable
0:30:23and the and the conclusion of the meeting
0:30:26and nineteen ninety eight meeting came back and i and say okay maybe we have
0:30:31more on this removal
0:30:33currently convert remote quite three you and whatnot
0:30:38the mainstream or what we walk
0:30:41next slide please
0:30:48very happy because after each time i had the problem but we need to use
0:30:53the to meet and
0:30:55there are more rules interaction with him
0:31:00i'm not sure because my initiation improved a lot but stephanie i
0:31:08i was closer to him and more able to
0:31:12to discuss the without fear of with e
0:31:15i remember particularly discussion about
0:31:19the speaker or reason for forensic an investigative it application of the freedom to be
0:31:27that is we started with the
0:31:29do so drawing me many
0:31:32and also very
0:31:34no i discussion in two fifteen sixteen when he
0:31:39came to me after the presentation of my paper with the way the g
0:31:45the ball really video speaker characteristics and he say go
0:31:49i would like to continue all are not going to start the phd unto the
0:31:54able with the
0:31:56what we things we have now be able to start with the shah really mixing
0:32:00linguistics aspect and the speaker recognition so
0:32:05this is a very nice
0:32:07moment in my brain no
0:32:13i will be of individual to after on the maybe
0:32:19we can extract the and of my
0:32:24mostly consist
0:32:26because when they look at the at the video of jack had to the you
0:32:31know restore i realised
0:32:34how much necessary and i
0:32:38had a huge influence on my career and the on the what
0:32:43you why you research
0:32:46so i we just
0:32:50say i but
0:32:52for to what i really don't from him what they share with limited to about
0:32:58some more best and i don't know stuff like a wheelchair would be we will
0:33:03stand me and we show me for a long time and remind conferences and my
0:33:08which were
0:33:11a and i mean you could give to me you okay to say that will
0:33:15be but
0:33:22okay like to some friends well so well we use the or to general solution
0:33:29to propose something about perhaps the previous or some of what is an okay mister
0:33:35thank you can you show lights lies please the
0:33:49i was the organiser of that workshop in nothing is that the dog and of
0:33:55course of ready for the two and it was my first meeting these with jack
0:34:01and the
0:34:04wanted to
0:34:07to say
0:34:10what i feel about the influence for his work on the things we've done in
0:34:18europe so that score to the next slide please
0:34:22where you will see the next slide we will see the party seep than
0:34:30many people that you know that contributed to these workshop be nodding e
0:34:39what i want to stress is really what is on the next slide
0:34:44so if you go to the next slide
0:34:51and the times there was a the caucuses the which is a quality needing only
0:34:56t on the speech database
0:34:59and speech assessment
0:35:03that was before this work shall mean id for whatever swearing that jack that
0:35:09at the same time that me conclude that any he was already
0:35:16the british in this a knuckle full database
0:35:20which was the first the only for speech database that was produced
0:35:27i mean in this
0:35:28this database is a five thousand speech is
0:35:32that the
0:35:35say the control the sentences on the
0:35:39an and the sun the all sorts of items of fifty items i guess all
0:35:46the telephone so it's it was the first the green the database that inspired the
0:35:56some of the word i was doing in a in switzerland that the time where
0:36:01we record the swiss french polyphone
0:36:05database which was equivalent to the microphone
0:36:09and another database that we call clearly well she's
0:36:14for a speaker variability so that we had the about the fifty speeches that were
0:36:21able to already called several times the of the polyphone at a
0:36:29so that we had the intra speaker variability as well
0:36:33in the meantime jack actually are produced also lizzy voice of cross is tiny can
0:36:39eric which was the at nazareth the database
0:36:45and dior ideal that is the key lingual effort
0:36:49was really is the start of the european project called speechdat
0:36:54which was
0:36:57the started after that
0:37:00actually in nineteen ninety five variability
0:37:04which are created the
0:37:06databases for
0:37:09most of the european
0:37:12other languages
0:37:13and also
0:37:17i guess and
0:37:20database for
0:37:21speech over a that in america so there was a
0:37:28these so that project
0:37:30and of course that was
0:37:33all the work that jack has been has started
0:37:38with the switchboard was taken over in the
0:37:43ldc for and down that for recording
0:37:48but as a date that this is like fisher and mixer and many and that
0:37:54was also the in pure initial the inspiration for the not data collection which was
0:37:59the non dairy in than entering polyphone version
0:38:03so that was really the start of the or the work he has done from
0:38:08the for the microphone and the voiceover hispanic and eric out was really spread all
0:38:14over the world
0:38:16for these collection all the polyphone databases so i think and like to
0:38:22to recognize or the work that has done in the in pushing for all of
0:38:28those these the data collection and very good and the price
0:38:33so that the next slide is not i know there is an ex like but
0:38:37it's not very
0:38:38it's and
0:38:39it's just the picture from the microphone
0:38:43data collection process but it's not very interesting
0:38:47so that's that was my conclusion
0:38:51thank you very much
0:38:53okay you're a monster
0:38:55so do you might wanna be a really global or anymore is able to texas
0:39:01instruments on performance sensible things
0:39:05list model
0:39:07you you're for only one session together and part of it
0:39:13i'm gonna
0:39:16a couple of other memories for a second one what everyone right contribution
0:39:23and evaluation dataset to remind right
0:39:29i wanna from the other side or
0:39:33formerly on and more recently as well and you know
0:39:40i have privilege working with amount of money are really far i see your out
0:39:46there somewhere
0:39:48and you only other directions are i like
0:39:53is he's
0:39:58and what i remember work in different areas of course and
0:40:06i remember being test the artifact them for right i guess in a straight into
0:40:12your all incidents down
0:40:14now the neighbours and
0:40:17so anyhow the songs and i think many of us have clearly so
0:40:22finally in which are commonly used and all of us engineering or c
0:40:29interest in our culture you in line with one
0:40:34and that of my first experience that
0:40:38i also had privilege of the in one of the corporate he recorded and that's
0:40:45but what i remember that is the one for restaurant on the unit was and
0:40:51i think if it is needed in the southwestern style right now
0:40:56i don't know everything analysis mathematics and so question here
0:41:01and then we enjoy the moment in many years that about a fantasy effectively now
0:41:12at sort of early on where i had no and then a more recently proceed
0:41:17with very or a and
0:41:21so i'm gonna start using and not getting having means and is the low say
0:41:27might expect that he was a little bit from the writing it is not someone
0:41:32who really
0:41:34and i think it's time in industry and government
0:41:43no the since the disaster the problem is the really i what he'll say is
0:41:50this is the only thing we have for one
0:41:53and had a strong interaction with that
0:41:58and you would say some through the l is the okay for another center agents
0:42:05i think the prefive a little bit differently fancy expectations about the really wanna make
0:42:12it anything we system
0:42:14towards a shot the problem
0:42:16we had a zero eer from last the listening for us and hang out with
0:42:22the solver
0:42:25we are very grateful for what you percent has a and b and sort of
0:42:31evaluations and matrix and is a fast
0:42:35for the
0:42:38and then added to retire the on our seamless the list and z and with
0:42:44higher bic your after the somewhere
0:42:48and sort of went back is true and channel four and it's each time and
0:42:53you are zero one myself
0:42:56i to have them with that but we're so much humour these days we did
0:43:02what we call this the science thing with a
0:43:05so that sort of with the poles are comfort obviously start it is true academic
0:43:11in the data and as a science than that in
0:43:14you the and you don't these models and for us and
0:43:21yes i second what everybody saying was it is a realistic in two
0:43:25where in different
0:43:31i think you're emotional
0:43:33so maybe scores in an somehow some and also something remotely sensed on the influence
0:43:42with two
0:43:48and they're in general form
0:43:51for organising the session
0:43:55to say that seen me so we started session here
0:44:01i don't like i was sitting across from jack daniels
0:44:04a unique words in building a small words of in my understanding the other understanding
0:44:11of problems in jacket this way you are kind of talking with people
0:44:16that was very
0:44:18but it's following but also in a collaborative way never and i really am stay
0:44:24on the you know is kind of understood that this was kind of a room
0:44:28and a collaborative effort to train two million four
0:44:32so i'm just a few words in step two gently for students in for the
0:44:38academic field i think time i pointed out he's done in the nn exploration move
0:44:45into the government industry in i think he's perspective on the academic field
0:44:52where is kind of somehow influenced after going to industry into and into the government
0:44:57no set yours a so
0:45:00you know no it just started to exactly mimicry of georgetown is usually inverse text
0:45:06a to do a postdoctoral position of the you are still for star airspace medical
0:45:13research lab and that actually i think about a lot more on physiology aspects so
0:45:19objects work inside into there's linguistics background
0:45:23and after that he joins in a year is in texas at dallas here and
0:45:29extension here's your you g d in slope maybe it'll sciences a most of is
0:45:34that what was really focused in the carter centre color centre was found nineteen forties
0:45:39actually by e
0:45:42are three founders a ti johnson examining bringing this river system for one for johnson
0:45:48which actually the person is found colours ten and they are just one for is
0:45:53non speech production him psycholinguistics
0:45:57i talked many quotes is there a he did we eventually real eh jean of
0:46:05including a number of errors and i know just actually used a question medical centre
0:46:11and the dollar sign an age project that show that just actual ear as essential
0:46:18has extent to actually what it also is effective utility to discriminate in class prior
0:46:25phonetic features in speech this is
0:46:28well it is the m zero is gonna work understanding the science and how the
0:46:33signs actually motivated maybe somebody technology advances in should feel so it's balance or something
0:46:40that which really i think that justin but also something good okay and it gave
0:46:44people there are more the technology side better understanding science
0:46:48the forensic science to better understand in technology
0:46:52well as you but jealousy worked there quite a bit with a lot still min
0:46:57ross perot's ram or it would be
0:47:01a good move a variety of the that researchers in also supervised belongs to a
0:47:09joy still which measures usually student actually to follow him to g i would be
0:47:15shifted or gi
0:47:17a i thought we were still min it's this week a one of is what
0:47:21collections is that usually there is to a most systems everybody will be more clinically
0:47:27oriented towards a phonetic speech science
0:47:31well to begin well we use asking questions and variance fiery by jack's was the
0:47:39man is one of your
0:47:41i when the engine is related you gaussian random scroll celebrating is twenty fifth anniversary
0:47:47we had set up distinguished lecture
0:47:53process and be projected the you distinguished lecture for twenty fifth anniversary okay
0:48:01and subject you know being however
0:48:04having a good sense if you my estimated i need a picture you chair
0:48:09and in suggest that well you know the only actually that could you know really
0:48:12in that room and there was a picture of him holding no more the largest
0:48:17fish i've ever seen any insisted you might and you use this picture you know
0:48:22for the for the keynote and i
0:48:25we had with him as i felt you know it's probably something that i was
0:48:29gonna get five from what might be in my question so i meant that a
0:48:33mormon and you know you really like to use this picture again that are using
0:48:38a better than you see here is reached i and
0:48:43just gave expensive two days with us okay
0:48:47in october two thousand eleven is connotes on which i think backwards i think we
0:48:54can buy light of the five minutes you i auditorium the engineerings for we based
0:48:59on and you met many students in one of things that their students are is
0:49:05appreciated was
0:49:08both this knowledge is worse than this way of balancing
0:49:12i guess so it
0:49:13say that
0:49:14just understood forms of workout not
0:49:20something were words and say always
0:49:24five value or whatever it's a
0:49:27then it was it is gonna of one of the digits are you had news
0:49:33meeting with very well one of our are all stock staff members just probably and
0:49:38we've been with us for many years and i got it should holding this one
0:49:43sets for
0:49:45cover mechanisms of speech by german by name alexander graham bell and just and where
0:49:52you initiated or its science and technology so maybe my common to be jot notes
0:49:58committed to helping students in the academic community
0:50:02you know listing and yes reason lr use as well as i cast in interspeech
0:50:07is gonna talking be collecting gerard injury have also pointing out that you know you
0:50:15make it make a way to go to those jurors to a one on one
0:50:20language and you know it's fell
0:50:24you had his undivided attention your attention
0:50:28we seven interactions there now see you really understood have to a inspires to actually
0:50:35motivates to understand that they were great opportunities for them in your rear and
0:50:43a new helping thing one many students are two very productive right
0:50:50in one of us to be used as you got can
0:50:53it plays and gender probably and i had the weather spending for they were generated
0:51:02four hours that numbers i just two minutes for our own and we found this
0:51:10i think
0:51:12well kitchen that was kind of like the whole mirrors in jack a we do
0:51:17we show in a look at things from different perspectives and you can see a
0:51:23lots of comments there but i think doing that the a
0:51:29pretty much everywhere we went with me
0:51:32given some historical knowledge of a few you know but i can and if knowledge
0:51:39of just
0:51:42everything historical
0:51:44the motivation for the online specs were just not robust one something jack in every
0:51:52so maybe just in closing house data
0:51:55well if you look at the nist and so is now we competitions it certainly
0:51:59challenge speech community
0:52:02really motivating from many researchers and teams and feel
0:52:06a competitions also offer extensive opportunities for common speech used to just very speech speaker
0:52:14and language or your wrist can so i think one of the looking at evaluation
0:52:19and benchmarking
0:52:21gender effort seems to have also used
0:52:24challenges and stories now read
0:52:27really one three inspirational wine for maybe students feel
0:52:32i'll say he of course need strategic fusion of speech science and technology it is
0:52:39also inspired motivated in mention countless young researchers to
0:52:44in the linking enhanced or where you know someone there really just wanted to make
0:52:50sure where
0:52:52if you want away from conversation jack one layer a better person your value understanding
0:52:58in more
0:53:00suggest a with a little snow you for so many years
0:53:04and you would be remiss fire mainly are probably weeks
0:53:08well most importantly all the friends and family if we can contact with
0:53:13i hear someone okay
0:53:14what we wanna
0:53:16it remains for everything you contribute to the fuel and since the site
0:53:23apparently remotes some it's been really inspiring to are used or is one of the
0:53:29something to remotes for one on my husband's to margin
0:53:42so this work we will go over the main point
0:53:51i don't see people have baseline well you know
0:53:56and war conditioning
0:54:12so as you for your decision for my only a single file and you probably
0:54:17all whereas if you john godfrey contribution size and sufficiency argument
0:54:25you can even
0:54:27his personality was already okay a few
0:54:34an amazing what you vector and one more community and we all
0:54:40i've got you can partly by one or more one issue as an are you
0:54:51for each iteration fisher
0:54:54where q our are actually in a more efficiently
0:54:58especially if you expressed if you have some experience here fishing
0:55:03you know as a few us what are you last year
0:55:09are contribution a legacy our fear
0:55:12well i
0:55:15it will be naming policy option bass or more
0:55:21younger of three this year
0:55:25you know go free so that or exactly strong i mean or feel and how
0:55:32she by one norm asking you about
0:55:36and what jack on a and
0:55:40what action
0:55:42and it would be and he will be greatly missed
0:55:45well this all one would allow someone okay be one or i mean
0:55:52i don't we all remember
0:55:54john asks more well assuming you see the first winter we see john best or
0:56:03a one-best or
0:56:06and all that if initial something infinite all five k i don't know that what
0:56:13it won't one question okay you
0:56:21thank you very much machine appreciate the language too
0:56:27finally and we would like to invite brian godfrey
0:56:32to give some words and the half of the godfrey family and what are not
0:56:39there it is to have brian representing the family today right
0:56:44based on or something everybody
0:56:49from a sitting
0:56:51this to you put this together and fusion the on the in our family accessing
0:57:08as my doesn't mind noted and an outstanding memorial on jack was a renaissance man
0:57:15i and different on about on that were results just randomly
0:57:18but i guess i can i losing everyone standard but multiple languages
0:57:25you know have a creation and technology good as we talked about here you talked
0:57:29about his stand academia industry
0:57:32all snotty little excursion appliances buildings and outdoors
0:57:39comprehension literature history economics along the successor
0:57:47listed is balanced analysis on
0:57:52unrelated reasons you could be easily areas but sometimes you can be
0:57:57smart analysis and within the to unit this study
0:58:03not of everything adjustments is that it
0:58:06and then sawdust only
0:58:11well brothers not master
0:58:13the background model
0:58:17as was ordinance no rates on integrity
0:58:20a generalist really fair and open minded readers
0:58:25all things it will for reverb discussed
0:58:31thank goodness of my brother sometimes also instantly stations
0:58:37right along all about that stuff also
0:58:40he's into an unlimited amount of energy
0:58:43and the decision was done on doing twirl one something
0:58:49you data manager originally you don't and others
0:58:53which embrace from this time
0:58:55regions and store managers and a right
0:59:00really and still an intense desire to one and then do things with the knowledge
0:59:07three task one of the common
0:59:10it seems i noticed and the nodes are received one or more of the people
0:59:14was only focus on the mentor
0:59:18it only once the best comedy the received one i one time student and years
0:59:24note that you don't and then the best teacher
0:59:29well after reading
0:59:30no memorials and you're not everybody set here
0:59:34i realise if we see that in a long history stuff
0:59:38teaching be a professor so i'll be use the influence you have also values calling
0:59:45yes i was bruno was applied in the real us to really implementing was
0:59:50in that also struck me
0:59:52the speakers and politics not all the
0:59:56so many names of people that i never had the opportunity need in detail about
1:00:01how incredibly smart people how it was addressed as far
1:00:06but what they were able to do
1:00:08and speaking with you several million over the past months replenisher
1:00:15so no the feelings mutual
1:00:17most a stalling so
1:00:19also you know i held everybody them also saw perfect embodiment model professor
1:00:25no surprise i can be
1:00:27first renew noisily that's where you know where he is waiters or was that was
1:00:32is wrong
1:00:35so now on the side of the challenge
1:00:39and right you know use an and just you know
1:00:45it's only many times you were used for the next question else
1:00:49and since all about what else is a year
1:00:53unless personally i don't know anybody more
1:00:57and well i don't know the specifics
1:01:00i do not exhaustion
1:01:03i know the speakers
1:01:05usually always closest friends intolerance it only
1:01:08what he brought of the field of human language technology will make a little better
1:01:12place was no less
1:01:15enclosing and not accumulating better
1:01:19almost close to the minimum orders of that's where in the streets enslavement
1:01:24just as a simple sentence somewhere for describing then
1:01:27and the loss is the last time
1:01:30you know personally and professionally
1:01:33so again thank you guys so much
1:01:36for including
1:01:38myself and my family in this and
1:01:41really means a lot so
1:01:47thank you very much brighter
1:01:49that's very touching the here from the family and
1:01:53your father was an amazing
1:01:57i'd also like to thank the panelists and the attendees
1:02:02and the odyssey teen ugh on a
1:02:05key go and talk a for me for helping us put this together and my
1:02:12colleague tell me can in for
1:02:17all the organising their you did together with me
1:02:22i wanna remind everybody to
1:02:26at end of the upcoming virtual tore of tokyo that starts at nine fifteen uses
1:02:35a different link
1:02:36so be sure to
1:02:40this came from this and go to the page to see that
1:02:44thank you that looks really nice and it'll be
1:02:49there appear after this session i also want to point out the
1:02:56tell me what's gonna point out the
1:02:58the other session go ahead tell me
1:03:02no nor is true
1:03:05also going to one and also show your work has been really on a normal
1:03:11to remove organs in this isn't so is reasonably
1:03:15suppose you are
1:03:19yes so are very well as well as on the eval or someone benchmark a
1:03:25two minutes or something so on sore everyone so the turks influence on the on
1:03:31the on benchmarking
1:03:34so based on this one to one
1:03:37so this summer
1:03:41okay maybe this is what channel
1:03:46yes thank you can only i think
1:03:50the other thing i wanna dimension is
1:03:53there is a session and evaluation in benchmarking chaired by omit from nist
1:04:03the duh directly follows
1:04:06in the frame of jack's leadership
1:04:11and guiding the community that's a and the man and them and session so you
1:04:17can view that at your leisure
1:04:21do you please joining the tokyo tore and that's all we have affected a i'm
1:04:27sorry were four minutes overtime
1:04:29thank you everybody i really appreciated
1:04:35thank you
1:04:38and smell on anyone