This task takes a single audio file containing speech data from the speaker to be trained, and creates a new speaker template file.
To create a speaker template from a single audio file
Send an AddTask
action to IDOL Speech Server, and set the following parameters:
Type
|
The task name. Set to IvSpkIdTrainAudio . |
File
|
The audio file that contains sample speech from one person. |
Out
|
The name of the speaker template file to create. You should include the iVector template file extension (.iv ). |
For example:
http://localhost:15000/action=AddTask&Type=IvSpkIdTrainAudio&file=C:/Data/BrownSpeech.wav&out=Brown.iv
This action uses port 15000
to instruct IDOL Speech Server, which is located on the local machine, to create the Brown.iv
template file by using the BrownSpeech.wav
file.
This action returns a token. You can use the token to:
To process streamed audio, you use the same task (IvSpkIdTrainAudio
), with the InputType
parameter set to Stream
. For more information, see the IDOL Speech Server Reference.