Developing voice segments

This section starts with an overview of voice signal processing, then goes on to tell you how to decide which way to record your voice segments and how to create them using the Blueworx Voice Response windows and the batch voice import (BVI) supplied utilities which are described in The Batch Voice Import process.

Overview of voice signal processing
Normally, voice is transmitted to the human ear by means of an acoustic wave travelling through the air at the speed of sound. A conventional analog telephone transmits sound through a wire as an electrical signal which travels at close to the speed of light. To do this, the acoustic signal generated by the human vocal chords must first be converted to an electrical signal, and then converted back to an acoustic form before it can be heard by the human ear. These two conversions are done by a telephone mouthpiece and earpiece respectively.
Planning your voice segments
Step-by-step instructions on how to create voice segments are given later in this section, but there are different approaches to this, so it is worthwhile taking some time to plan what you are going to do:
The voice segment database
In this section there is a diagram showing German, French and US English voice databases. In the US English database, the structure is shown. This comprises a voice table, a voice directory for the language containing voice segments, and a system voice directory also containing voice segments.
Creating a voice directory
Use this procedure to create a new voice directory for storing the voice segments you will record. If you want to add new voice segments to an existing voice directory, use the Voice Segments window to list the existing voice directories and make a note of the voice directory ID of the required directory.
Using the Blueworx Voice Response windows for voice segments
This section describes how to use the Blueworx Voice Response windows for voice segments to check disk space
Defining a voice segment
Use this procedure to add IDs and descriptions of new voice segments to a voice directory:
Checking recording levels
When setting levels, ensure that you are not overdriving the audio adapter, or you will get clipping distortion. Use the following procedure as a quick way to check the recording level:
Recording voice segments using the telephone
The Record_Comp and Record_Uncomp voice applications are supplied with Blueworx Voice Response to allow you to record voice segments via a telephone using one of the Blueworx Voice Response channels. Record_Comp is used for recording in compressed format and Record_Uncomp for uncompressed (also known as clear channel) format.
Grouping voice segments in a voice table
Voice segments can optionally be grouped in a voice table, which is simply an organizational tool to help you locate segments more easily. You can group voice segments that are similar, such as names of your products, names of people, cities in your business area, and so on.
Importing and exporting voice segments
You can record voice segments on equipment other than an Power System computer and import your recordings to Blueworx Voice Response. You can also alter the format of the imported audio data, as required. You can export Blueworx Voice Response audio data to other systems.
Editing voice segments
You can edit both the description and the graphical representation of the voice segments that you create. Note that the minimum segment size for editing is 20 milliseconds. Use this procedure to edit voice segments in a selected voice directory.
Copying voice segments
To copy an existing voice segment, you can use one of the methods described here: