DecodableAmNnetSimple Class Reference

#include <nnet-am-decodable-simple.h>

Inheritance diagram for DecodableAmNnetSimple:

Collaboration diagram for DecodableAmNnetSimple:

Public Member Functions
	DecodableAmNnetSimple (const NnetSimpleComputationOptions &opts, const TransitionModel &trans_model, const AmNnetSimple &am_nnet, const MatrixBase< BaseFloat > &feats, const VectorBase< BaseFloat > *ivector=NULL, const MatrixBase< BaseFloat > *online_ivectors=NULL, int32 online_ivector_period=1, CachingOptimizingCompiler *compiler=NULL)
	This constructor takes features as input, and you can either supply a single iVector input, estimated in batch-mode ('ivector'), or 'online' iVectors ('online_ivectors' and 'online_ivector_period', or none at all. More...
virtual BaseFloat	LogLikelihood (int32 frame, int32 transition_id)
	Returns the log likelihood, which will be negated in the decoder. More...
virtual int32	NumFramesReady () const
	The call NumFramesReady() will return the number of frames currently available for this decodable object. More...
virtual int32	NumIndices () const
	Returns the number of states in the acoustic model (they will be indexed one-based, i.e. More...
virtual bool	IsLastFrame (int32 frame) const
	Returns true if this is the last frame. More...
Public Member Functions inherited from DecodableInterface
virtual	~DecodableInterface ()

Private Member Functions
	KALDI_DISALLOW_COPY_AND_ASSIGN (DecodableAmNnetSimple)

Private Attributes
CachingOptimizingCompiler	compiler_
DecodableNnetSimple	decodable_nnet_
const TransitionModel &	trans_model_

Detailed Description

Definition at line 282 of file nnet-am-decodable-simple.h.

Constructor & Destructor Documentation

DecodableAmNnetSimple()

DecodableAmNnetSimple	(	const NnetSimpleComputationOptions &	opts,
		const TransitionModel &	trans_model,
		const AmNnetSimple &	am_nnet,
		const MatrixBase< BaseFloat > &	feats,
		const VectorBase< BaseFloat > *	ivector = NULL,
		const MatrixBase< BaseFloat > *	online_ivectors = NULL,
		int32	online_ivector_period = 1,
		CachingOptimizingCompiler *	compiler = NULL
	)

This constructor takes features as input, and you can either supply a single iVector input, estimated in batch-mode ('ivector'), or 'online' iVectors ('online_ivectors' and 'online_ivector_period', or none at all.

Note: it stores references to all arguments to the constructor, so don't delete them till this goes out of scope.

Parameters

[in]	opts	The options class. Warning: it includes an acoustic weight, whose default is 0.1; you may sometimes want to change this to 1.0.
[in]	trans_model	The transition model to use. This takes care of the mapping from transition-id (which is an arg to LogLikelihood()) to pdf-id (which is used internally).
[in]	am_nnet	The neural net that we're going to do the computation with; we also get the priors to divide by, if applicable, from here.
[in]	feats	A pointer to the input feature matrix; must be non-NULL. We
[in]	ivector	If you are using iVectors estimated in batch mode, a pointer to the iVector, else NULL.
[in]	ivector	If you are using iVectors estimated in batch mode, a pointer to the iVector, else NULL.
[in]	online_ivectors	If you are using iVectors estimated 'online' a pointer to the iVectors, else NULL.
[in]	online_ivector_period	If you are using iVectors estimated 'online' (i.e. if online_ivectors != NULL) gives the periodicity (in frames) with which the iVectors are estimated.
[in,out]	compiler	A pointer to a compiler [optional]– the user can declare one in the calling code and repeatedly supply pointers to it, which allows for caching of computations across consecutive decodes. You'd want to have initialized the compiler object with as compiler(am_nnet.GetNnet(), opts.optimize_config).

Definition at line 58 of file nnet-am-decodable-simple.cc.

                                        :
    compiler_(am_nnet.GetNnet(), opts.optimize_config, opts.compiler_config),
    decodable_nnet_(opts, am_nnet.GetNnet(), am_nnet.Priors(),
                    feats, compiler != NULL ? compiler : &compiler_,
                    ivector, online_ivectors,
                    online_ivector_period),
    trans_model_(trans_model) {
  // note: we only use compiler_ if the passed-in 'compiler' is NULL.
}

Member Function Documentation

IsLastFrame()

virtual bool IsLastFrame ( int32  frame ) const

inlinevirtual

Returns true if this is the last frame.

Frames are zero-based, so the first frame is zero. IsLastFrame(-1) will return false, unless the file is empty (which is a case that I'm not sure all the code will handle, so be careful). Caution: the behavior of this function in an online setting is being changed somewhat. In future it may return false in cases where we haven't yet decided to terminate decoding, but later true if we decide to terminate decoding. The plan in future is to rely more on NumFramesReady(), and in future, IsLastFrame() would always return false in an online-decoding setting, and would only return true in a decoding-from-matrix setting where we want to allow the last delta or LDA features to be flushed out for compatibility with the baseline setup.

Implements DecodableInterface.

Definition at line 336 of file nnet-am-decodable-simple.h.

References KALDI_ASSERT, and KALDI_DISALLOW_COPY_AND_ASSIGN.

                                              {
    KALDI_ASSERT(frame < NumFramesReady());
    return (frame == NumFramesReady() - 1);
  }

KALDI_DISALLOW_COPY_AND_ASSIGN()

KALDI_DISALLOW_COPY_AND_ASSIGN ( DecodableAmNnetSimple  )

private

LogLikelihood()

BaseFloat LogLikelihood ( int32  frame, int32  index  )

virtual

Returns the log likelihood, which will be negated in the decoder.

The "frame" starts from zero. You should verify that NumFramesReady() > frame before calling this.

Implements DecodableInterface.

Definition at line 78 of file nnet-am-decodable-simple.cc.

References DecodableAmNnetSimple::decodable_nnet_, DecodableNnetSimple::GetOutput(), DecodableAmNnetSimple::trans_model_, and TransitionModel::TransitionIdToPdfFast().

                                                                    {
  int32 pdf_id = trans_model_.TransitionIdToPdfFast(transition_id);
  return decodable_nnet_.GetOutput(frame, pdf_id);
}

NumFramesReady()

virtual int32 NumFramesReady ( ) const

inlinevirtual

The call NumFramesReady() will return the number of frames currently available for this decodable object.

This is for use in setups where you don't want the decoder to block while waiting for input. This is newly added as of Jan 2014, and I hope, going forward, to rely on this mechanism more than IsLastFrame to know when to stop decoding.

Reimplemented from DecodableInterface.

Definition at line 330 of file nnet-am-decodable-simple.h.

Referenced by main().

                                              {
    return decodable_nnet_.NumFrames();
  }

NumIndices()

virtual int32 NumIndices ( ) const

inlinevirtual

Returns the number of states in the acoustic model (they will be indexed one-based, i.e.

from 1 to NumIndices(); this is for compatibility with OpenFst).

Implements DecodableInterface.

Definition at line 334 of file nnet-am-decodable-simple.h.

{ return trans_model_.NumTransitionIds(); }

Member Data Documentation

compiler_

CachingOptimizingCompiler compiler_

private

Definition at line 345 of file nnet-am-decodable-simple.h.

Referenced by DecodableNnetSimple::DoNnetComputation().

decodable_nnet_

DecodableNnetSimple decodable_nnet_

private

Definition at line 346 of file nnet-am-decodable-simple.h.

Referenced by DecodableAmNnetSimple::LogLikelihood().

trans_model_

const TransitionModel& trans_model_

private

Definition at line 347 of file nnet-am-decodable-simple.h.

Referenced by DecodableAmNnetSimple::LogLikelihood().

---

The documentation for this class was generated from the following files:

• nnet3/nnet-am-decodable-simple.h
• nnet3/nnet-am-decodable-simple.cc