hi all,
last night, i did a bridge between sphinx3 and pd. sphinx3 is an open source speech recognition software.
have a look at the demo http://www.vimeo.com/2814913
i am looking for help for optimizing or even better making an external for it.
working on linux only for now.
using shell to call a python script (py/ext is crashing when import
_sphinx3)
(mrpeach) - i like this solution, cause i can use the same script to have speech recognition in blender or other osc compatible software
is it possible to write a raw soundfile in pd (1 channel, signed, 16000 (samplerate))?
about dynamic patching
for basic stuff (http://wiki.puredata.info/en/Category:vanilla)
pat
moin patrick,
this is excellent! is the code available somewhere?
marmosets, Bryan
On 2009-01-13 16:58:21, patrick puredata@11h11.com appears to have written:
hi all,
last night, i did a bridge between sphinx3 and pd. sphinx3 is an open source speech recognition software.
have a look at the demo http://www.vimeo.com/2814913
i am looking for help for optimizing or even better making an external for it.
working on linux only for now.
using shell to call a python script (py/ext is crashing when import
_sphinx3)
- communication between the python script and pd via open sound control
(mrpeach) - i like this solution, cause i can use the same script to have speech recognition in blender or other osc compatible software
- using shell again to call sox (for converting the soundfile to raw).
is it possible to write a raw soundfile in pd (1 channel, signed, 16000 (samplerate))?
- dynamic patching with send pd-$0.sphinx (obj 20 20 $voicerecognition)
- would like to be able to connect objects together, need to learn more
about dynamic patching
- it's possible to make a custom dictionary, for now i will create one
for basic stuff (http://wiki.puredata.info/en/Category:vanilla)
- tested with two big accents : french (me) and japanese (my girlfriend)
pat
Fun stuff!
.hc
On Jan 13, 2009, at 3:14 PM, Bryan Jurish wrote:
moin patrick,
this is excellent! is the code available somewhere?
marmosets, Bryan
On 2009-01-13 16:58:21, patrick puredata@11h11.com appears to have written:
hi all,
last night, i did a bridge between sphinx3 and pd. sphinx3 is an open source speech recognition software.
have a look at the demo http://www.vimeo.com/2814913
i am looking for help for optimizing or even better making an
external for it.
working on linux only for now.
using shell to call a python script (py/ext is crashing when
import _sphinx3)
- communication between the python script and pd via open sound
control (mrpeach) - i like this solution, cause i can use the same script to have speech recognition in blender or other osc compatible software
- using shell again to call sox (for converting the soundfile to
raw). is it possible to write a raw soundfile in pd (1 channel, signed,
16000 (samplerate))?
- dynamic patching with send pd-$0.sphinx (obj 20 20
$voicerecognition)
- would like to be able to connect objects together, need to learn
more about dynamic patching
- it's possible to make a custom dictionary, for now i will create
one for basic stuff (http://wiki.puredata.info/en/Category:vanilla)
- tested with two big accents : french (me) and japanese (my
girlfriend)
pat
-- Bryan Jurish "There is *always* one more
bug." jurish@ling.uni-potsdam.de -Lubarsky's Law of Cybernetic
Entomology
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
http://at.or.at/hans/
thanks,
i am looking for help (suggestions, ideas, optimizations, dynamic patching etc). you can find the download + instructions (3 easy steps!) here:
http://probing.wikidot.com/sphinx3-to-pure-data
basic commands are: BANG B AE NG CANVAS K AE N V AH S HORIZONTAL HH AO R AH Z AA N T AH L INLET IH N L EH T INPUT IH N P UH T LOADBANG L OW D B AE NG MESSAGE M EH S IH JH MESSAGE(1) M EH S AH JH NUMBER N AH M B ER OUTLET AW T L EH T OUTPUT AW T P UH T RADIO R EY D IY OW SLIDER S L AY D ER SYMBOL S IH M B AH L TOGGLE T AA G AH L TWO T UW VERTICAL V ER T IH K AH L
pat
hi
could u explain a bit what you like to dynamically patch? i am quite interested in this area :)
you might want to have a look at [dyn~] or pd-msgs in the pd-extended help
i am about to write a little helper abstraction to chain abstractions together. and that handles the connections (send~) between them. would that be interesting for you?
eni
patrick wrote:
thanks,
i am looking for help (suggestions, ideas, optimizations, dynamic patching etc). you can find the download + instructions (3 easy steps!) here:
http://probing.wikidot.com/sphinx3-to-pure-data
basic commands are: BANG B AE NG CANVAS K AE N V AH S HORIZONTAL HH AO R AH Z AA N T AH L INLET IH N L EH T INPUT IH N P UH T LOADBANG L OW D B AE NG MESSAGE M EH S IH JH MESSAGE(1) M EH S AH JH NUMBER N AH M B ER OUTLET AW T L EH T OUTPUT AW T P UH T RADIO R EY D IY OW SLIDER S L AY D ER SYMBOL S IH M B AH L TOGGLE T AA G AH L TWO T UW VERTICAL V ER T IH K AH L
pat
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list
hi,
yes very interesting. also, i was looking at pdmtl abstractions dyn.poly, but for now all i want is to be able to connect objects together, for example:
<speaking> number box connect oscillator connect output == [number2] | [osc~] | [dac~]
how to connect multiple outlet?
<speaking> trig bang float anything connect 3 print bang print float print anything == [t b f a] | | | [print bang] ... ...
not sure, looking foward for suggestions! pat
hi patrick
have u seen : Help/manuals/pd-msg/1.msg_and_patch/1.2.create_patch.pd ?
this is from pd-extended help browser. i'm not sure where you can find it in svn.
patrick wrote:
hi,
yes very interesting. also, i was looking at pdmtl abstractions dyn.poly, but for now all i want is to be able to connect objects together, for example:
<speaking> number box connect oscillator connect output == [number2] | [osc~] | [dac~]
how to connect multiple outlet?
<speaking> trig bang float anything connect 3 print bang print float print anything == [t b f a] | | | [print bang] ... ...
not sure, looking foward for suggestions! pat
hello it sounds really nice! please keep inform i might be able to help you with osc/python/pd if you need
you could also add speech synthesis... (mbrola works pretty nicely)
some remarks below
patrick a écrit :
hi all,
last night, i did a bridge between sphinx3 and pd. sphinx3 is an open source speech recognition software.
have a look at the demo http://www.vimeo.com/2814913
i am looking for help for optimizing or even better making an external for it.
working on linux only for now.
using shell to call a python script (py/ext is crashing when import
_sphinx3)
or make a python script which calls pd...
- communication between the python script and pd via open sound control
(mrpeach) - i like this solution, cause i can use the same script to have speech recognition in blender or other osc compatible software
great
- using shell again to call sox (for converting the soundfile to raw).
is it possible to write a raw soundfile in pd (1 channel, signed, 16000 (samplerate))?
is it absolutely necessary for sphinx to use raw file format?
- dynamic patching with send pd-$0.sphinx (obj 20 20 $voicerecognition)
- would like to be able to connect objects together, need to learn more
about dynamic patching
- it's possible to make a custom dictionary, for now i will create one
for basic stuff (http://wiki.puredata.info/en/Category:vanilla)
- tested with two big accents : french (me) and japanese (my girlfriend)
did you manage to recognize french words (with a french accent ;-) ?
best v
pat
Pd-list@iem.at mailing list UNSUBSCRIBE and account-management -> http://lists.puredata.info/listinfo/pd-list