ECE597 Project NodeRed Voice

From eLinux.org
Revision as of 10:54, 13 November 2014 by MattOlson (talk | contribs)
Jump to: navigation, search

thumb‎ Embedded Linux Class by Mark A. Yoder


Team members: Dmitry , Matt Olson

Grading Template

I'm using the following template to grade. Each slot is 10 points. 0 = Missing, 5=OK, 10=Wow!

00 Executive Summary
00 Installation Instructions 
00 User Instructions
00 Highlights
00 Theory of Operation
00 Work Breakdown
00 Future Work
00 Conclusions
00 Demo
00 Late
Comments: I'm looking forward to seeing this.

Score:  10/100

(Inline Comment)

Executive Summary

Our project has branched out along several paths since it's inception. The goal was to create a personal assistant that could listen to commands, talk back, and perform them. For modularity, our original goal was to use IBM's Node Red to accomplish this. However, Node Red is not designed for the complicated and workflows that we needed, and extensions were not scale-able. In this document we are going to describe three things.

  • A simple node red speech recognition and synthesis system
  • Using the open source jasper project on Raspberry Pi
  • Using the open source Jasper project on Beaglebone Black

The simple node red speech synthesis will essentially listen to the user, and the repeat back what is said. Currently the speech synthesis is working, and we are trying to integrate pocket sphinx for the speech recognition.

Jasper was developed with the Raspberry Pi, and as a result has a very simple set up procedure. Our goal is too use this platform to begin developing modules. We currently have working versions of jasper installed and have 2 modules developed.

There are no reliable installation instructions for setting up Jasper on the Beaglebone black. We have done the research, and are hoping to be able to provide concise installation instructions and port over our work.

Packaging

Jerry Talyor of Mansfield, IN is going to make a fantastic wooden laser cut and laser engraved box for us.

Installation Instructions

Installing Node Red on Beaglebone Black

Setting up Wifi "=In Progress="

Installing Node Red

host$ git clone https://github.com/node-red/node-red.git
host$ cd node-red
host$ npm install --production

Installing extra Nodes "=In Progress="

Installing PocketSphinx

Download latest realizes from CMU Repo of both sphinxbase and pocketsphinx. The version currently being used is 0.8 Go to sphinxbase root directory and run

./autoconf.sh
./configure.sh
make 
make install

Installing Jasper on raspberry Pi

Follow the instructions provided on the documentation page to install JASPER http://jasperproject.github.io/documentation/software/

The modules we have implemented use the python RPI.gpio library, run the following commands to install it

sudo apt-get update
sudo apt-get install python-dev
sudo apt-get install python-rpi.gpio

Installing our custom Modules to demonstrate Jasper

git clone https://github.com/dmitryvv/woodoo
cd woodoo
chmod +x install_modules_RPi.sh
./install_modules_RPi.sh

Installing Jaser on Beaglebone Black

See above details for setting up wifi and installing PocketSphinx.

User Instructions

Jasper on Raspberry Pi Instructions

To start jasper, move to the jasper directory and run

python jasper.py

Highlights

Here is where you brag about what your project can do.

Include a YouTube demo.

Theory of Operation

Our project uses the opensource Jasper project as it's backbone. The system is constantly listening to it's surroundings, and when it finds a discrete sound block sends it to the google voice API for analysis. Google voice returns text blocks of what it thought the sound click was of. Jasper then runs it across modules looking for a hit, and then executes a command if it finds one.

Completed Tasks

Matt Olson

  • Node Red Installed - 10/20/2014
  • Wi-fi dongle working - 10/22/2014
  • Created Module for Jasper - 10/28/2014
  • Created install script for installing modules on RPi - 11/12/2014

Dmitry Votinstev

  • Speech recognition software installed - 10/20/2014
  • Sound recording/payback with arecord aplay works 10/22/2013

Tasks Remaining

  • Pass input text into Node Red - Matt
  • Produce text from speech synethsizer - Dmitry

Future Work

Suggest addition things that could be done with this project.

Conclusions

Node Red does not provide a very good architecture for acting as a speech recognition system and dispatcher, which resulted in our choice to investigate other options.




thumb‎ Embedded Linux Class by Mark A. Yoder