Analysis of Confusion Matrix to Combine Evidence for Phoneme Recognition

Abstract

In this work we analyze and combine evidences from different classifiers for phoneme recognition using information from the confusion matrices. Speech signals are processed to extract the Perceptual Linear Prediction (PLP) and Multi-RASTA (MRASTA) features. Neural network classifiers with different architectures are built using these features. The… (More)

Topics

1 Figure or Table

Slides referencing similar topics