“…A few techniques, such as linear mapping [2], piecewise linear mapping [3,4], codebook mapping [5,6], neural networks [7,8], Gaussian mixture model [9,10], and hidden Markov model [11,12] and non-negative hidden Markov model [13], have been explored. Linear predictive coefficients (LPCs) or line spectral frequencies (LSFs) [14,15] are widely used to represent the spectral envelope, while the excitation can be found by inverse filtering the signal with LPCs, modulation techniques, non-linear processing, and the application of function generators [1].…”