LSP weighting functions based on spectral sensitivity and mel-frequency warping for speech recognition in digital communication

Abstract

In digital communication networks, a speech recognition system extracts feature parameters after reconstructing speech signals. In this paper, we consider a useful approach of incorporating speech coding parameters into a speech recognizer. Most speech coders employ line spectrum pairs (LSPs) to represent spectral parameters. We introduce weighted distance… (More)
DOI: 10.1109/ICASSP.1999.758147

6 Figures and Tables

Topics

  • Presentations referencing similar topics