Skip to main content

Advertisement

Table 1 Identification accuracy with different mixture numbers for clean data of Grid and TIMIT datasets.

From: Auditory Sparse Representation for Robust Speaker Recognition Based on Tensor Structure

Features Grid(%) TIMIT(%)
  16 32 64 128 16 32 64 128
ANTCC 99.9 100 100 100 96.5 97.62 98.57 98.7
LPCC 100 100 100 100 97.6 98.1 98.1 98.1
MFCC 100 100 100 100 98.1 98.1 98.57 99
PLP 100 100 100 100 89.1 92.38 90 93.1