kaldi::differentiable_transform Namespace Reference

Classes

class  AppendTransform
 This is a version of the transform class that consists of a number of other transforms, appended dimension-wise– e.g. More...
 
class  DifferentiableTransform
 This class is for speaker-dependent feature-space transformations – principally various varieties of fMLLR, including mean-only, diagonal and block-diagonal versions – which are intended for placement in the bottleneck of a neural net. More...
 
class  FmllrTransform
 Notes on the math behind differentiable fMLLR transform. More...
 
class  MinibatchInfoItf
 
class  NoOpTransform
 This is a version of the transform class that does nothing. More...
 
class  SequenceTransform
 This is a version of the transform class that does a sequence of other transforms, specified by other instances of the DifferentiableTransform interface. More...
 
class  SimpleMeanTransform
 This version of the transform class does a mean normalization: adding an offset to its input so that the difference (per speaker) of the transformed class means from the speaker-independent class means is minimized. More...
 
class  SpeakerStatsItf