IO_Speaker_Segmenter Class Reference

The AM adaptation application does not need any speaker clustering information. The prepare adaptation application handles clustering. Unfortunately the adaptation application needs to read and write the speaker clustering information from and to disc. For this purpose this small class is created with only read and write methods. More...

List of all members.


Public Member Functions

 IO_Speaker_Segmenter (FILE *inFile)
 ~IO_Speaker_Segmenter ()
int getNumberOfClusters ()
void storeClusters (FILE *outFile)

Protected Attributes

int numberOfClusters
TrainPhoneModeltrainCluster [INITIAL_NUMBER_OF_CLUSTERS]

Detailed Description

The AM adaptation application does not need any speaker clustering information. The prepare adaptation application handles clustering. Unfortunately the adaptation application needs to read and write the speaker clustering information from and to disc. For this purpose this small class is created with only read and write methods.

Constructor & Destructor Documentation

IO_Speaker_Segmenter::IO_Speaker_Segmenter ( FILE *  inFile  ) 

This constructor will read speaker segmentation information from inFile.

References numberOfClusters, and trainCluster.

IO_Speaker_Segmenter::~IO_Speaker_Segmenter (  ) 

The destructor clears allocated data.

References trainCluster.


Member Function Documentation

int IO_Speaker_Segmenter::getNumberOfClusters (  ) 

This method returns the number of clusters. If no clusters are available, one is returned. (all data is assigned the same clusterID)

References numberOfClusters.

void IO_Speaker_Segmenter::storeClusters ( FILE *  outFile  ) 

This method stores the speaker clustering information to disc (loaded by the constructor).

References numberOfClusters, trainCluster, and PhoneModel::writeModel().

Here is the call graph for this function:


Member Data Documentation