/ Data / Fundamentals / Production / Tutorials / Software / Home
Section 2: Overview

Since speech recognition systems use many knowledge sources, there is a significant amount of data that must be prepared before recognition experiments can begin. Data preparation and conversion is one of the most time-consuming and frustrating tasks related to speech recognition. In this section, we discuss the details of file format conversions and data preparation.

Section 2: Contents

2.1   Overview
  2.1.1   What is a Speech File?
  2.1.2   Contents of a Speech File
  2.1.3   Common Speech File Formats
  2.1.4   The SPHERE Format
  2.1.5   The WAV Format
  2.1.6   The Sof Format

2.2   File Conversion
  2.2.1   Supported Formats
  2.2.2   Converting SPHERE Files to RAW Format
  2.2.3   Verification of Conversion to RAW
  2.2.4   Creating Sof Files

2.3   Downsampling
  2.3.1   Why Change the Sample Frequency?
  2.3.2   How Does Downsampling Work?
  2.3.3   Implementation

2.4   Auxiliary Resources
  2.4.1   TI Digits
  2.4.2   Audio and Transcription Databases

2.5   Command Synopsis
Section 2: Data Preparation
Table of Contents   Section Contents   Previous Page Up Next Page
      Glossary / Help / Support / Site Map / Contact Us / ISIP Home