The LangIdFeature task converts an audio file containing a single language into a language identification feature (.lif) file. Language identification feature files are required for training language classifiers.
| Parameter | Description | Required |
|---|---|---|
| Type | The task type. Set to LangIdFeature. |
Yes |
| Beam | The beam width of the search process. | |
| DnnFile | The Deep Neural Network acoustic modeling file to use. | |
| File | The audio file to process. | Yes |
| Lang | The name of the language pack to use. | Yes |
| Out | The language identification feature (.lif) file to create. | Yes |
| SilThresh | The threshold between what the task identifies as silence and non-silence. | |
| SpeechThresh | The threshold between speech and non-speech (music or noise). | |
| SugdInputChannels | The channel layout of the input media file. | |
| SugdInputFrequency | The sampling rate of the input media file. |
http://localhost:13000/action=AddTask&Type=LangIdFeature&File=C:\Data\FrenchSpeech.wav&Out=frenchSpeech.lif
This action uses port 13000 to instruct Speech Server, which is located on the local machine, to create the frenchSpeech.lif file from the FrenchSpeech.wav file.
|
|