机译:基于HMM的语音合成中激励建模的统计方法
School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University, Seoul 151-742, Korea;
School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University, Seoul 151-742, Korea;
School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University, Seoul 151-742, Korea;
School of Electrical Engineering and the Institute of New Media and Communications, Seoul National University, Seoul 151-742, Korea;
HMM-based speech synthesis; waveform interpolation; principal component analysis; non-negative matrix factorization;
机译:基于HMM的语音合成中激励建模的统计方法
机译:基于音高的频谱激励基于HMM的语音合成模型
机译:在基于HMM的文本到语音合成中纳入混合激励模型和后置滤波器
机译:基于HMM的语音合成的基本频率轮廓建模:用于统计语音合成的基本频率轮廓表示
机译:基于感知响度和语音统计模型的语音增强。
机译:寻求语音的时间可预测性:比较18种世界语言的统计方法
机译:基于残留建模的基于HMM的语音合成激励模型