SPEECH RECOGNITION IN MAX
This project is for people that are suffering the lost of their human voice because of tobacco smoking.
My company needs to develop a prototype that will help people using a speaking valve to transform the robotic type voice into a more human like one.
Can anyone please give let me know if there is any documentation that might be helpul? Also were hiring for this project if anybody feeling capable is interested.
thx.
so what are you working on : voice recognition or voice synthesizing ?
Both topics are vast and very different and well researched and there is a load of universitarian documentation available on these at a quick google search's distance.
Thx for your reply. Both. I know there is load of documentation about these topics. Im looking for specific documentation in MAX, thats why im posting in this forum ! Actually would be great if i can see actual MAX patches working.
Oh okay.
what i know of : a vocal vowels synthesis patch in the CNMAT library distribution, mxj op.recognize https://cycling74.com/tools/op-recognize/ for recognition, https://github.com/numediart/mage for vocal synthesis in real-time : mage is awesome and open source but hard to compile and use i think
Thx so much vichug ! I really appreciate your help !!
hth
Interested in this thread. I want to speak into max and have it recognize individual words, separate them at spaces then send them out of a patch letter by letter as ascii.