profany

yesterday i had a ideia to create a patch that made voice recognizing.

for date i needed to save audio data to later i can campare this audio data with current audio data.

Somebody know how save audio data and compare it with others audio data

hi
yesterday i had a ideia to create a patch that made voice recognizing.
for date i needed to save audio data to later i can campare this audio data with current audio data.
Somebody know how save audio data and compare it with others audio data


save-audio-data-and-how-to-compare-audio-siganl

i suspect this is a very complex non-trivial subject-- in some ways you'd be better off applying for a scholarship to do post-graduate study in the field. but if you want to at least explore the fundamentals of it you could do searches for "neural networks", "formant identification", "audio descriptors" and other such terms and see what you come up with-- there are some resources within the world of maxmsp, like ej's descriptors package and nd's nn externals, but you'd probably find you'd need to make your own feature extraction and comparison externals, after at least many months of focussed research

i suspect this is a very complex non-trivial subject--  in some ways you'd be better off applying for a scholarship to do post-graduate study in the field. but if you want to at least explore the fundamentals of it you could do searches for "neural networks", "formant identification", "audio descriptors" and other such terms and see what you come up with-- there are some resources within the world of maxmsp, like ej's descriptors package and nd's nn externals, but you'd probably find you'd need to make your own feature extraction and comparison externals, after at least many months of focussed research


Save audio data and how to compare audio siganl