An auditory-based distortion measure with application to concatenative speech synthesis
John H. L. Hansen, David T. Chappell · IEEE Transactions on Speech and Audio Processing · 1998
This study presents a new auditory-based distance measure with application to concatenative speech synthesis. This measure employs the Carney auditory model to produce a feature vector related to auditory perception. For concatenative synthesis, the new measure is employed to assess perceived discontinuities at segment transitions. Evaluations using a restricted data base environment show that the new measure can be effective in improving speech synthesis performance.