name: LogAreaRatio : public AlgorithmBase


g++ [flags ...] file ... -l /isip/tools/lib/$ISIP_BINARY/lib_algo.a

#include <LogAreaRatio.h>

LogAreaRatio(ALGORITHM algorithm = DEF_ALGORITHM, IMPLEMENTATION implementation = DEF_IMPLEMENTATION, long order = DEF_ORDER);
boolean eq(const LogAreaRatio& arg);
boolean setAlgorithm(ALGORITHM algorithm);
boolean compute(VectorFloat& vector_out, const VectorFloat& vector_in, AlgorithmData::COEF_TYPE input_coef_type = DEF_COEF_TYPE, long index = DEF_CHANNEL_INDEX);
quick start:

LogAreaRatio lar;
VectorFloat input(L"1, 0, -1");
VectorFloat output;
lar.compute(output, input, AlgorithmData::REFLECTION);

The LogAreaRatio class is used to compute the log area ratio coefficients from a linear predictive model. A more detailed discussion of this approach can be found in: The input signal can either be the reflection coefficients or the prediction coefficients. LATTICE algorithm and KELLY_LOCHBAUM implementation is currently supported.

The mathematical descriptions of these algorithms are provided below for reference purposes:

Log area ratios have historically been useful in speech coding and synthesis applications, since they directly describe (in theory) the vocal tract area function. They have not been used extensively in speech recognition applications.


public constants:

error codes:

protected data:

required public methods:

class-specific public methods:

private methods: