[Asterisk-Users] Anybody using Sphinx

[Arnold Ligtvoet]

Chris Albertson wrote:
> I've played around with it.  I'm certainly NOT and expert but I'm
> pretty shur yu do NOT need a sound card.  Sphinx will be happy to
> read an audio recording from a file.

Oke this might explain it. I was trying to run sphinx-server, but got an
error there leading me to believe that I;
a) needed a soundcard
b) needed to install alsa driver (which seems silly without a sound card).

The 'trick' would be to let the caller pronounce the name, record this as a
wave, compare it, give feedback and so on.

> As for language, Spinx doesn't know or care if you speeak
> spanish or Korean it's all just sounds, numbers and symbol
> strings.  Spinx does not _understand_ anything.

Since I would like the user names to be auto-generated by the system, I
would guess that this could best be done using festival with a localized
voice. I think there is a Dutch voice for Mbrola with should integrate into
festival ( note to self : need bigger harddisk :-) )

> Spinx would work fine for a dial by name system but you would
> have to plan for the case where it can not find a match or finds
> more then one match.  ASking the user to say both first and last
> anems may help.  But poor audio quality is the #1 problem and
> 8Khz sampled "telephone quality" is at the low end of what
> will work..  You'd prefer 16 bit samples and 48Khz sample rate
> and a first quality mic.

I scripted around this in the Cisco app, by asking for a name once and if
there is no match giving the caller the option to key in the extension
number or wait for an operator. In case of multiple matches the script plays
something like: "I found multiple matches. Type 1 if you want to speak to
xx, type two (and so on)". This method seems to work.

Thanks Chris for your input, I'll give it a go.

Arnold