My startup need speech recognition experts for outsourcing about our
project. We want to work on CMU Sphinx because that platform looks really
promising and easy for developing.
We need to develop speech recognition server (like Google's) and neural
network system that will learn from users in near future. Idea is to run
server on Linux machine.
For client devices, we need to develop just basic trigger word recognition
on low power ARM board.
We have plan to develop new acoustic models (different languages).
Budget for this software prototype is: 1000-2000$
Currently we are working on hardware prototype of our project. For this
stage we need test software.
Here is the workflow we need:
1) Consulting about ideas and finalizing requirements
2) Developing simple speech recognition service for client device (ARM,
trigger words, streaming to server)
3) Developing server side software for prototype
4) Fixing bugs and finalizing prototype
We need someone who know principles behind speech recognition and someone
who can tune everything for final product.
Apply for job with your previous experience and jobs.
Feel free to contact me for any question.
Thanks,
Stefan
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello guys,
My startup need speech recognition experts for outsourcing about our
project. We want to work on CMU Sphinx because that platform looks really
promising and easy for developing.
We need to develop speech recognition server (like Google's) and neural
network system that will learn from users in near future. Idea is to run
server on Linux machine.
For client devices, we need to develop just basic trigger word recognition
on low power ARM board.
We have plan to develop new acoustic models (different languages).
Budget for this software prototype is: 1000-2000$
Currently we are working on hardware prototype of our project. For this
stage we need test software.
Here is the workflow we need:
1) Consulting about ideas and finalizing requirements
2) Developing simple speech recognition service for client device (ARM,
trigger words, streaming to server)
3) Developing server side software for prototype
4) Fixing bugs and finalizing prototype
We need someone who know principles behind speech recognition and someone
who can tune everything for final product.
Apply for job with your previous experience and jobs.
Feel free to contact me for any question.
Thanks,
Stefan
Last edit: Ashok Singh 2017-07-06