Data Naming Scheme

In the initial data set, the audio file and its transcription file must share the same file name (excluding the path and file extension). This allows you to use a single list to specify both audio files and text files.

For example, suppose you have the following files:

You could specify the list of training data as:

train1
train2
train3

The audio files share the same file names as their transcription text files, so this list fully specifies both the training files and the pairing between the files.

For more information about IDOL Speech Server's list manager, see Create and Manage Lists.

Both the audio files and the transcription files require further preparation before they can be used in the adaptation process. See Prepare the Audio Data and Prepare the Transcription Data.


_HP_HTML5_bannerTitle.htm