基于感知加权线谱对距离的最小生成误差语音合成模型训练方法

雷鸣，凌震华，戴礼荣

Minimum Generation Error Training Based on Perceptually Weighted Line Spectral Pair Distance for Statistical Parametric Speech Synthesis

LEI Ming,LING Zhen-Hua,DAI Li-Rong

模式识别与人工智能 . 2010, (4): 572 -579 .