subvq_t Struct Reference

Wrapper structures of sub-vector quantization. More...

#include <subvq.h>

List of all members.

Public Attributes

arraysize_t origsize
int32 n_sv
int32 vqsize
int32 ** featdim
vector_gautbl_tgautbl
int32 *** map
float32 * subvec
int32 ** vqdist
int32 * gauscore
int32 * mgau_sl
int32 VQ_EVAL

Detailed Description

Wrapper structures of sub-vector quantization.


Member Data Documentation

featdim[s] = Original feature dimensions in subvector s

Subvq-based approx. Gaussian density scores for one mixture

Vector-quantized Gaussians table for each sub-vector

int32*** subvq_t::map

map[i][j] = map from original codebook(i)/codeword(j) to sequence of nearest vector quantized subvector codewords; so, each map[i][j] is of length n_sv. Finally, map is LINEARIZED, so that it indexes into a 1-D array of scores rather than a 2-D array (for faster access).

Shortlist for one mixture (based on gauscore[])

#Subvectors

origsize.r = #codebooks (or states) in original model; origsize.c = max #codewords/codebook in original model.

float32* subvq_t::subvec

Subvector extracted from feature vector

int32** subvq_t::vqdist

vqdist[i][j] = score (distance) for i-th subvector compared to j-th subvector-codeword

#Codewords in each subvector quantized mean/var table


The documentation for this struct was generated from the following file:

Generated on 7 Mar 2010 by  doxygen 1.6.1