hello everyone and as you know i'm from the speech technology it sounds and today
i'm going two presents some information about c company
well
the speech technology its answer was found it in a nineteen ninety
and it was funded by the roll call for young scientist
and today
we
the company has been are working on the innovation technologies during twenty four more than
twenty five years
and today we have the
why stuff more than a three hundred and fifty a people who are working on
a different here we're on the speech technologists
the most of them all the scientists and engineers
our company has
twenty eight p h d degree
the people and here
the mean are
or well
a d r o all about set to yell so
well and the about the here we have of our research
and zero
our
solutions for the industry
we are working on speech recognition speech since it is always and basically a matrix
and speech and that in a six
well
the rap a range or for our interest and the of course we are very
interested in developing a good solutions for the
voice back down by an entry
a well you can see there
many of our customers
in our in
in the side in the rock try or international companies
l so we
collaborate with the assembly nowhere stays for example
well no well no one it's more university we has
our department there and
we
ditch our students and say
p h is you dance
well
also or
i
as i and all of the you know in the right this cocoa project started
a near a few years ago
and we participated the up to
well this to see manage to build just well irene tedium a in the industry
it is the one of the leading parent it in the wall
or was then the one hundred and twenty a technical specialists they are
i have mentioned it
well about the minimum energy management standards
we are fully certified
i so well nine
ninety or one company
liz i would it'd
financials and the
i can say that we have well balanced mentioned to him
and
this it's
about the company just in fewer
tension
okay given okay
thank you mean
so now i don't know cuddles
it is he's going to present something about zero one week
so with modeling every my thank you for coming so i'm gonna talk a little
bit about
zero is like by and mainly at i think the main purpose of these of
this session is to do hear from you so
so i had this open question is what that it's what to the role of
in this to be in this advancing the indy scientific a community so that's right
my performance by
trying to
set
so about zeros like
so a lot of
maybe some of you know this is a you know supplier of audio and volumes
and that was and there it should wait and somewhere solutions so we'd about habitat
somewhere
in terms of what we morgan a whole chain for all you change from the
microphone from these and microphone say at combat pairs dsp to the process of the
application process i'm back to the lower speaker and we also what software so it's
is
it is interesting for us which is
no need for signal processing not suppress the on and what in my profession and
of course
speaker recognition
and we focus some of my solo c rs optimal by the time and a
can summarily applications and in this feels in speaker recognition is mostly needed for authentication
so we you know already we don't focus on politics it's
okay or a feel is mostly authentication it's
we domingo size components from one house and place it is
all spread around the world and us a euro s
and it is one thing i want to mention which is i think it's good
for this is an american
so the court or is very important so we have this kind of slow as
like silver from san the you know like that in your when you're right that
and you spend a boss dataset and all that stuff so it's just say okay
that's then school and no
i think within about this is that they are really the really get about the
employee so they and this everything for as a selling receptionist because
i mean
divided we motivated that do in your
you or your so if you
if you need to be in the scientific community in you need to collaborate with
other teams and you need to you know us error and the defence we do
here they understand that and they say okay that's it that's the way you work
in this way so they don't aids i mean it's
it's a matter of you know keeping the ideas of the of the
the researchers have otherwise in one
the one of the
let's see how we set thing in and that's important for this from a combination
where cultural is very important
so
that's all i wanted to say
so that all zeros lower one or several power
presentation is about the remote of interest in the scientific community so how eight
what's are you and i want to select we you and maybe
get some feedback any directories
let us know how
come we had but can we do so
so in our previous update in the industry have assessed themes and processed things
i idea is that they should have one foot on the on the scientific community
and of course of emitting state of the company and in the end to combine
is the one can you
this of what you're right
but egg
the but it's we have a so in the industry and let's say that we
know
that we are more aware of the challenges of the we use cases that a
magi day the reset so actually data you select two sources of innovation one is
the and what we call technology both and you're one is my
so technology post what we generate here so
if you're serving bs and we get this is this new technology it's gonna change
speaker might be it's gonna be better than before but is not really oriented to
any use case or any porpoise but we have also the other which is the
market was so maybe it's important to face noise phase reverberation i don't know what's
but in s use case what's gonna be
how is gonna be the morning five year so that's
that's the thing that companies may be may know more about that because they do
some complex and they have a marketing change from the inside looking to that so
this kind of information
and a help us define the challenge s and i think that's that maybe or
are our best contribution yes help to define it telling us how things to be
evaluate how and
once what have a customer a suspect team while a how the future is gonna
be how do we see some to set and maybe a
contribute to that so that's two main points and
something here so
so in this case of hadley finding the time yes
but also we have a full in the scientific communities i think
it's important then we keep it very competitive correlation so if we define very long
but long term goals a
it several okay framework to collaborate and seventy s a
are not very close to the problem so does
so that's
our bill
i want to know
so that's what
so the role of the industry being the scientific community
okay that's all i want to see
as follows now it's time and then you will have a few minutes
i know you can do it
okay
i'm gonna be very brief what'll people the top because i think that was your
you know idea that we just
talking twenty minutes but unfortunately the forensic people be than the low us to detect
so much time but
so the main the main goal of my speech now it's gonna be just give
you a brief introduction recognition because i don't know how many people here is aware
of we are we are they and you see we are like the tiny little
company between these two other guys we rst like
i like this evening like c as like it is small power of x techniques
you know that we are resisting to
to be guys
so like means a sanitised company that was created in two thousand and four and
it was a as an a startup of id sc-ubm grouping method
in the university and buddy technical university matrix actually it's funny "'cause" now twelve years
ago we where publicly presented in a novel use a congress the last one that
was organized here is pain and still to this one about back and of an
important little
so
so it's been a long time now we have we have three main locations married
of course where the heck what is are we have and of using in washington
where we're supporting the us business or whether and capetown where or
so that we can guys are helping us to solve problems like you collaborate and
so on
in total we are around twenty five people
as on a small company we are still growing and in fact that we lost
some people not so long ago move into two zero is because we decided to
just so sailor or
they mobile business of the company to zeros and now all these guys are
are working with them
and we are probably the most doesn't think that agnitio has is that we are
probably the only company out there that is fall fully focus on automatic speaker recognition
that's all we do we don't do a speech
we don't do any other language-related a technology we will be bored i in both
paramedics so we train would try to be as good as good as we can
for that
and today a or b guest book pretty nice is still in the in the
global market because of it with born we porting the forensic community because actually the
very large enough the company's a joint program between the ubm the university madrid and
what if you need in this pain that they just a to invest some money
in the group and so on and that's
the a priori enough of the goal but actually our forensic two
it was the very first problem we developed for them
actually i do using previously
that they the people talk about the level for quite awhile
during the presentations today according to the last interpol survey that the backend lightyear
we are around roughly fifty percent of the for in c class that are doing
the automatic speaker recognition out there
so
in the case then we are finally we
we got some traction and some
some success can be seen people that we are good
and i case and i don't want to extend much more you are interesting the
problem we're gonna be layer in the
in the silent so until the session so more than happy to show you what
we control because we have problems about also institutional but for those that
that we can we will
and
and as and in fact
we are
rate full of well being here
the embedded because
actually our view it's pretty close to what kind of the explain that we are
truly believers of the these become data give a community and we try to share
as much as we can then we try to the us open as
as we can because we really think that is the only way to make these
technology a evolve and the good thing is that we can provide
some insights from reality that sometimes is important because sometimes you guys need some ground
to two types and to understand what are the real problem so there and not
only just reduce that point one in the equal error rate
because maybe you are you're just reducing point one and equal error rate and you
are multiplied by ten the memory that you're using so maybe that's important also to
have that that'll to be that is okay and it works great but i wanted
to work in a laptop or
or like these guys of y two working now mobile phone that is even more
difficult you know
so
so and that's why we keep we keep a very close relation with many with
many people actually around and
and
and that's pretty much it and i hope that
you tell us because i want this to be not for some very long but
i wanted to be here we meet interactive then we would love to understand what
do you guys the spectrum as also because the of course we get advantage of
you working on these speaker we learn and then that's also always useful
but we also want to learn from you know and that's why i think be
that would opportunity to be here and discuss
thank you
that sounds and i think that basically the view that follows the is more or
less
a lot of components are
unless he responded so basically i think that we have to the nominees
to listen you and
or to listen that cutting
so the first question or the first topic we can we can talk about not
a long time
e c and
how in the how i can only see the relation between economy and just and
then we can discuss some of that if you used in these interesting
so
anyone wants to talk
okay
for lid
yes it is easy to explain what academic a expecting from you it's morning
so you know that but
to be a little bit more precise we need more may to do open research
we have good relation was industrie for applied research we all missing all of this
morning for
new innovation you know ten years we have movies unimodal because whole one of the
morning we have is that the two
close them on a project so if you want to help of you academy just
you to give or information b s p l c formation was maybe no more
than four pitch you can be your
and just if we if we to use the remote this he asked to for
a competition we would propose
the topic and you will to give a paid for the kids t
in this case we could have really open topics
and the we could make the market for you in ten or twenty use but
so
okay any of you want to
the player to just comment
okay that's
that's a little bit
that money is always select the tickets over some four
compensate i mean they are they are therefore probably we don't forget that so
i we can do that we can do that but it's the subways i mean
when you
i mean when accompanist a what you money somewhere
he they expect some
some redone so we have some collaboration with big universities a
going on which is really based on subcontract in and
leading then and go ahead go ahead with research and so on
but it's
it's actually unless it could be it could be possible that you
several companies get together and agreed to find something like
but you're mentioning its i don't see why couldn't be done i agree with that
but if there is only a few of then it's
it's a little bit controversial because you're funding for the comparison as well so that's
that's always complicated doesn't obligated is so components is only one
a star finally in some projects with for the academia but there are
involve a small groups maybe some
not is not quite open
but it could be the case that we could get together and five something bigger
not would be and i'm not directly but
they are real that
and i would like to add a due to that
that
strongly i strongly agree with you at that we need to give you long term
because i think that is t and i think that these myself i do and
i pretty for the disguise also have pretty clear where we would like to go
and ten years
is true that
that as a scholar said we need to find a balance between them between investing
in research open investigation and the party that any company wants to wants to want
to get right so that but i think that i and actually i think that
different companies over here
we are kind of all band and we try to parties actually which we try
to but was as much as possible that sometimes believe me is not so easy
now company just to get the also relation just to get popping whatever you are
getting right so
but i think it's all about the find a balance because the at some point
we want to help and then in the other and the other hand
the owners of our companies want to get some profit for from that right so
that's a key i think that find that balance between these two things
i would i would like to say well of course have to agree completely with
some possible to apply a dream for us but anyway a there's another
option that day starts to be almost mandatory it want to get funding from the
european union of these that most more involvement
on the core of the companies only thing
initiatives
because with a i'm talking about you from a europe is pretty perspective
with f p seven framework programme seven of the european union
a the big projects where mostly the well it rate it will escort when huge
enrollment all companies was present with a rice and twenty the new paradigm for your
parents funding
the involvement of industry have become has that's even increased
and the many of the proposals have rejected because they are not space that the
that those places this a but they are asking for companies to lead the proposed
accordingly the proposals to get more involvement in the proposal
not just as integrators or facilitators but just four
doing the research themselves
and generate a products that are
i the they're going to be integrated and on a high-level at entertainment as it
a little bit
so
perhaps a good the mum
middle point between something or research
totally and a doing what we're doing currently which is collaborating as a subcontract would
be to get the mobile then in this kind of initiatives with which of course
there risque because sometimes they are not found that many times the other funny there's
truly competitive
at least in my i'm at the environment around
most of the time i see a big project grant it is because the companies
cody at eight we have this speaker identification integrated project now from f p seven
that is correlated by parent
that's a good example that's when companies gets a huge involvement of this then we
can expect to have a lot the funding for lots appear the students and whatever
else but it eight in it it's a for in my opinion it
it makes sense that the companies assume that risk that i would like to hear
the pin the of the companies
yes then you have to code in the template so induce the academy and government
or european okay
so many common about how government or you'll open that case
so that's
i mean i fully agree i in fact
assets the company recognition is a
we think that we are we're getting to h twenty that we didn't we didn't
do enough if be sure that and i'm gonna talk now from a comedy or
perspective not from being just in general because i'm i don't know many others but
for is huge afford only because as a twenty five people company and
be part of the combination of a project like these that you know how we
these that usually both like thirteen different companies from seven different countries you know that
it's creating only that discrete in like point emails per day and
and let a mum is it's tough stuff but this is so that we want
to be there and we're moving in that direction but is to
i don't know if this so much about
have been a common a big corporation the leaving the a the initiative it's more
about
been able to percent rio the usability for whatever you but we i think that
that's exactly that i think that the european union is able eighteen very possibly his
that
the capability that you have
to put whatever you the below
i'll they're doing things
use useful things right and i think i think that of course for that and
industry should be should be also uses there are some in users also or here
and i think that it's also important that they get involved as well in the
case of for in six the forensic labs in the case of
some other and billions the corpus is the government agency in the case they of
i identification of all of citizens the proper government brian so i think it's also
three party thing is not only about the you guys researchers we guys the company
but also the in users that also be about the about proposed to the project
i am also
okay like to comment it's
i completely agree with you but it there's
one problem we also hired in this in discourse a it's
that is that it's a lot of overhead
yes for going to the court so that's
that's a big running takes a long time a needs
sometimes from the company
point of view c then someplace if it's even easier to identify
the rather than
you know that go ahead then try to spend all these maybe from nothing
the problem the problem you
you have they're also is
is that
and i think essential we have in a in our side in the industry here
we have to fix it which is a
we should look into this pre-computed discolouration more but in the industry side so i
i always see this okay this competition in this utopia riots where you have one
or two company leading someone prior than the other two competing and it's maybe for
this one or for the other one and they don't get together and they have
a different same thing so it's
so that something some we may need to fix on our side so far were
computed experiments but i
i four that we would you that that's
problem either graph to get
to get well all we want
we all
okay any question
or comments down
so i ask a question i'm not sure if you're grew up there probably you
be unhappy with his question but
if you're looking at maybe in the feeling forensics and so forth there are researchers
the mean i in this room especially in speaker recognition space that in focus more
on the sre
but i think if you look at bs very in you look at maybe some
of the work in the forensic space there there's some more at their connected but
disconnected as well and also think that the ability to get access to realistic data
in the field is very challenging i mean it's not easy to get her case
data
to be publically released so i'm wondering from a company perspective
the willingness of your organisations to be able to share your data even if it
means it's in a controlled setting maybe of some type of work
other user license that allows individual labs to get access to that i would be
very important because i think as dark pointed out you know data drives a lot
of our work and i still think that there is a somewhat of a voice
separation if you will between the technologies
and the forensic speech scientist and i think access to the data will actually help
people on the technology side released on the research side in a lot better way
we're going
so
a probably this is the politically incorrect to say here but i fully agree that
most of the research community for the last five years
in my opinion is to
sre by s
because the most of the algorithm that you find here are focus on optimize whatever
we sold you get in the whatever condition of whatever evaluation all mixed and
and is true that
reality differs a lot from that i mean it's a good
you try having everybody log data and anything that needs has been doing a huge
work to provide data to everybody
but of course that is only representing a small portion of the different conditions that
you can find out there
and even for as we struggle to get data like that and of course we
have our own our own databases we try to build them but
but sometimes
is not chasing because most of the in users and for the morning for in
six
they are not so easy to get that data to share everybody and for s
and it's true that they are like a few initiatives from the use of for
instance what inferior the created a database to really make a i think that they
the d the something similar
but is to that
the idea still it's like what in jail was present in it it's just elected
a small databases is more for and i know and you know that there is
tong update after real data out there sitting
sitting down and
and is true that we need to do something because it is true that the
end users
that's not help
both community i mean you guys m and as guys it's very high it will
happen to advance and we can get
perfect in the in condition a b and c all means there's hardly twenty overall
weight that
what that means for really make sure so i know obviously if you were between
us or eer we see the movement if you're working at work or
mated looked at for speech no wild infrared dark speech to all receive are moving
things into more naturalistic data but you believing those corpora they show variability but they
don't be me not necessarily reflect word you would see sometime german in the voice
forensic side of things ensures
somehow would be nice you can see more about him and i'll just full disclosure
unbiased because with the ozarks speaker committee responsible for trying to work to find out
word data could be used for the or sex or
resisting
you know in our company would be always the something agreement with the customers and
we
and not i don't know abilities to redistribute usually this to you builds is data
for the
and community but
i agree with the u and of course i would like to sing these survive
for the speaker went in the wild challenge because it's which was agreed to punch
unity to investigate this key some data just noisy and or different conditions
in case of our company we also participate in the air but
the data we have is the usually unlabeled to and what we have also have
some issues how to use these in our research number topics and we usually
can get only the models will we can get the
we forms all the data so and
in my opinion it is maybe it's a good idea to share i-vectors why not
because no huge just a minute it's possible
well
okay so
we all wear what we'll over a decision is
for surplus have you hear
and thank you your opinion and comments