From: cpd@cat.pan.net
"RT" wrote in message
news:4C047DCD.1A384E79@hotmMOVEail.com...
> catpandaddy wrote:
>>
>> "RT" wrote in message
>> news:4BFD4065.7B3DF15C@hotmail.com...
>> > catpandaddy wrote:
>> >>
>> >> "RT" wrote in message
>> >> news:4BF0B3C4.FEF22197@hotmMOVEail.com...
>> >> > catpandaddy wrote:
>> >> >>
>> >> >> "RT" wrote in message
>> >> >> > catpandaddy wrote:
>> >> >> >> "Tim McGaughy" wrote in message
>> >> >> >> > RT wrote:
>> >> >> >> >
>> >> >> >> >>> Voice recognition is also actually very reliable. They're
>> >> >> >> >>> not
>> >> >> >> >>> things
>> >> >> >> >>> that devices can 'barely do'.
>> >> >> >> >>
>> >> >> >> >> Let us know when they pass a Turing test.
>> >> >> >> >
>> >> >> >> > That's an unfair evaluation when trying to determine how much
>> >> >> >> > progress
>> >> >> >> > has
>> >> >> >> > been made. You expect the performance of a finished product
>> >> >> >> > from
>> >> >> >> > a
>> >> >> >> > work
>> >> >> >> > in
>> >> >> >> > progress.
>> >> >> >>
>> >> >> >> I would and still do maintain that voice recognition systems
>> >> >> >> have
>> >> >> >> indeed
>> >> >> >> aced the Turing Test, in that they succeed and fail in similar
>> >> >> >> places
>> >> >> >> to
>> >> >> >> where human beings also succeed and fail. Ever meet a human
>> >> >> >> being
>> >> >> >> who
>> >> >> >> never
>> >> >> >> mis-hears something?
>> >> >> >
>> >> >> > Do you have a cite or three that such acing has occurred?
>> >> >>
>> >> >> It is a trivial observation that human beings and
>> >> >> speech-recognition
>> >> >> software both misunderstand spoken words alike, under the same sets
>> >> >> of
>> >> >> circumstances and for the same reasons.
>> >> >
>> >> > So, do you have a cite or three that such acing has occurred?
>> >>
>> >> Regarding speech recognition: Do you deny that both humans and
>> >> voice-recognition software hear words okay most of the time but are
>> >> sometimes thrown off for the same reasons? I think you can recognize
>> >> that
>> >> this is true, and therefore the voice-recognition program would pass
>> >> the
>> >> test handily, and it should be a simply matter for you to set up your
>> >> own
>> >> test if you only had some initiative of your own. On the other hand,
>> >> sometimes it is all too easy to mistake you for an Internet chatbot.
>> >> ;-)
>> >
>> > As you dodge again. Just like a chatbot.
>>
>> That's a good little parrot.
>
> For the third time, my fast-and-loose-with-reality friend
>
> do you have a cite or three that such acing has occurred?
For the third time, I point out to you that I'm simply expressing my belief
that it's already a daily occurrence, but you're clearly not going to accept
that, so I'll be direct here: If you need to know whether or not there is a
cite, you need to ask someone whose done the research, such as Tim or
whomever else.
As for our discussion, what I would really like to know is where YOU think
speech recognition software is at and how it has progressed. Not to wins
points in a cite-vs-cite contest, but just from natural human curiosity.
Where do you think speech recognition is today? Where do YOU think it needs
to be? At what point will its success/failure performance and circumstances
be close enough to a human performance to be sufficiently convincing in your
own estimation, if my criteria are in error?
To be clear: I myself am /not/ a scientist in the field of artificial
intelligence, and my interest is strictly that of a curious outsider. If
you can accept that and are willing to deal with me on those terms, then I
welcome your perspectives. If not, that's fine too. But more
cite-badgering isn't going to do any good. If all you're going to do is
come back and ask me for a cite again, I can guarantee that I will continue
to refer your request to someone in the actual field.
So, are we going to have a nice easy casual conversation or not... it's your
choice.
--- SoupGate-Win32 v1.05
* Origin: you cannot sedate... all the things you hate (1:229/2)
|
