acoustic signal processing; natural language processing; speaker recognition; Chinese speakers monophthongs; Chinese speakers vowel space; Euclidean distance; Mandarin Chinese; Mandarin monophthongs; Tibetan speakers monophthongs; Tibetan speakers vowel space; Tibetan vowel system; acoustic features; contrastive analysis hypothesis; experimental phonetic approach; monosyllabic words; native Tibetan speakers; speech learning model; standard Chinese; vowel space distribution; vowel space features; working vowel space; Acoustics; Educational institutions; Euclidean distance; Pragmatics; Production; Shape; Speech; Contrastive Analysis Hypothesis; Mandarin; Speech Learningcjee Model; Tibetan; monophthongs;
机译:利用说话者自适应训练来实现汉语-藏语跨语言语音合成
机译:德国母语师和普通话学习者生产的德国时态和龙猴元音的声学比较
机译:听力损失讲话者语音声学和铰接器运动的特点
机译:西藏扬声器普通话单滩的声学特征
机译:基于声音特征的频率扭曲,用于扬声器归一化。
机译:患有帕金森氏病的普通话母语者的声学和感知语音特征
机译:帕金森病的普通话讲话的声音和感知后果
机译:使用声学因子分析(预印本)进行稳健的说话人识别的集成特征归一化和增强。