LangIdSegStream

The LangIdSegStream task receives audio data as a binary stream, converts it into language identification features, and then processes the data in fixed-sized chunks. It returns the language identification results for each chunk.

Parameters

Parameter Description Required
Type The task type. Set to LangIdSegStream. Yes
Beam The beam width of the search process.  
ClassList A list of language classifiers to use.  
ClassPath The path to the directory containing the language classifiers.  
DnnFile The Deep Neural Network acoustic modeling file to use.  
Lang The name of the language pack to use. Yes
LangList A subset of languages to use from the classifier list file.  
MinPhoneRate The minimum phone rate (phones per second).  
NBest The maximum number of language candidates to include in the output file.  
Out The file to write language identification results to. Yes
SegSize The maximum results segment size.  
SilThresh The threshold between what the task identifies as silence and non-silence.  
SpeechThresh The threshold between speech and non-speech (music or noise).  

Note: The ClassList parameter is required only if you want to change the audio sample rate, or if you want to use your own custom classifiers. You might also need to specify the ClassPath parameter, depending on the location of the classifier files.

Example

http://localhost:13000/action=AddTask&Type=LangIdSegStream&ClassList=ListManager/OptClassSet&ClassPath=C:\LangID\&Out=SpeechLang6.ctm

This action uses port 13000 to instruct IDOL Speech Server, which is located on the local machine, to identify languages in the audio stream using the language classifiers specified in the OptClassSet list, and to write the identification results to the SpeechLang6.ctm file.


_HP_HTML5_bannerTitle.htm