METHOD AND APPARATUS FOR SPEECH RECONSTRUCTION WITHIN A DISTRIBUTED SPEECH RECOGNITION SYSTEM

摘要

A method and apparatus for speech reconstruction within a distributed speech recognition system is provided herein. Missing MFCCs are reconstructed (219) and utilized to generate speech (223) . Particularly, partial recovery of the missing MFCCs is achieved by exploiting the dependence of the missing MFCCs on the transmitted pitch period P (213) as well as on the transmitted MFCCs. Harmonic magnitudes are then obtained from the transmitted and reconstructed MFCCs, and the speech is reconstructed (223) utilizing these harmonic magnitudes.