The Simon Handbook

Peter H. Grasch (peter.grasch bedahr.org)

Revision 0.4 (2012-12-14)

Copyright © 2008-2012 Peter Grasch

Simon is an open source speech recognition solution.

Table of Contents

1. Introduction

2. Overview

Architecture

Required Resources for a Working Simon Setup

Scenarios
Acoustic model

3. Using Simon: Typical user

First run wizard

Scenarios
Base models
Server
Sound configuration
Volume calibration

The Simon Main Window

Main window: Scenarios
Main window: Training
Main window: Acoustic model
Main window: Recognition

Import Scenario
Delete Scenario

Volume
Silence
Content
Microphone
Sample Quality Assurance

Contribute Samples

Manage training data

Modifying samples
Clear training data
Importing Training Samples

Configuration

General Configuration
Recordings
Speech Model
Model Extensions
Recognition
Actions
Text-to-speech
Social desktop
Webcam configuration
Advanced: Adjusting the recognition parameters manually

4. Advanced: Creating new scenarios with Simon

Introduction

Speech recognition: background

Language Model
Acoustic Model

Scenario hierarchies
Adding a new Scenario
Edit Scenario
Export Scenario

Adding Words
Editing a word
Removing a word
Special Training
Importing a Dictionary
Create language profile

Import a Grammar
Renaming Categories
Merging Categories

Storage Directories
Adding Texts
On-The-Fly Training

Scenario selection
Sample groups
Context conditions

Executable Commands
Place Commands
Shortcut Commands
Text-Macro Commands
List Commands
Composite Commands
Desktop grid
Input Number
Dictation
Artificial Intelligence
Calculator
Filter
Pronunciation Training
Keyboard
Dialog
Akonadi
D-Bus
JSON
VRPN

5. Questions and Answers

6. Credits and License

A. Installation

List of Tables

2.1. Ways to an acoustic model
2.2. Base model requirements
3.1. Julius Configuration Files
4.1. Sample Vocabulary
4.2. Sample Vocabulary
4.3. Improved Sample Vocabulary
4.4. Sample Vocabulary
4.5. Improved Sample Vocabulary