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

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 measures to improve the recognition performance of an LSP-based speech recognizer. Experiments on speaker-independent connected-digit recognition showed that weighted distance measures provide better recognition accuracy than unweighted distance measures do. Compared with a conventional method employing mel-frequency cepstral coefficients, the proposed method achieved higher performance in terms of a recognition accuracy.