公开(公告)号：EP1453037B1

公开(公告)日：2010-06-09

申请号：EP04251145.1

申请日：2004-02-27

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Choo, Ki-hun ,  Lee, Jae-won ,  Kim, Jeong-su ,  Lee, Ki-seung

IPC分类号： G10L15/04

CPC分类号： G10L15/04

摘要： A method of setting an optimum-partitioned classified neural network and a method and apparatus for automatic labeling using an optimum-partitioned classified neural network are provided. The method of automatic labeling using an optimum-partitioned classified neural network comprises (a) searching for neural networks having minimum errors with respect to a number of L phoneme combinations from a number of K neural network combinations generated at an initial stage or updated, updating weights during learning of the K neural networks by K phoneme combination groups searched with the same neural networks, and composing an optimum-partitioned classified neural network combination using the K neural networks of which a total error sum has converged; and (b) tuning a phoneme boundary of a first label file by using the phoneme combination group classification result and the optimum-partitioned classified neural network combination, and generating a final label file reflecting the tuning result.

公开(公告)号：EP1308928A2

公开(公告)日：2003-05-07

申请号：EP02257456.0

申请日：2002-10-28

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Lee, Ki-seung ,  Kim, Jeong-su ,  Lee, Jae-won

IPC分类号： G10L13/06

CPC分类号： G10L13/07

摘要： Disclosed is a speech synthesis system and method using a smoothing filter. A speech synthesis system for controlling a discontinuous distortion occurred at the transition portion between concatenated phonemes which are speech units of a synthesized speech using a smoothing technique, comprising: a discontinuous distortion processing means adapted to predict a discontinuity occurred at the transition portion between concatenated samples of phonemes used for a speech synthesis through a predetermined learning process, and control a discontinuity occurred at the transition portion between the concatenated phonemes of the synthesized speech in such a fashion that it is smoothed adaptively to correspond to a degree of the predicted discontinuity. The smoothing filter smoothes the synthesized speech so that the discontinuity degree of synthesized speech follows the predicted discontinuity degree according to the filter coefficient (a) changed adaptively to correspond to a ratio of the predicted discontinuity degree to the real discontinuity degree. That is, since a discontinuity occurred at a transition portion between concatenated phonemes of the synthesized speech (IN) is adaptively smoothed to follow that occurred in the actually spoken sound, the synthesized speech (IN) can be approximated more closely to a real human voice.

摘要翻译： 公开了一种使用平滑滤波器的语音合成系统和方法。 用于控制不连续失真的语音合成系统发生在作为使用平滑技术的合成语音的语音单元的级联音素之间的转换部分，包括：不连续失真处理装置，用于预测在级联样本之间的过渡部分发生的不连续性 用于通过预定学习过程进行语音合成的音素，并且以合成语音的级联音素之间的过渡部分发生不连续性，使得它被自适应平滑地对应于预测的不连续性的程度。 平滑滤波器对合成语音进行平滑，使得合成语音的不连续度遵循根据预测的不连续度与预测不连续度与实际不连续度的比率而自适应地改变的滤波器系数（a）的预测不连续度。 也就是说，由于在合成语音（IN）的级联音素之间的过渡部分发生不连续性被自适应地平滑以跟随发生在实际语音中的发音，所以合成语音（IN）可以更接近于真正的人声 。

公开(公告)号：EP1453037A3

公开(公告)日：2006-05-17

申请号：EP04251145.1

申请日：2004-02-27

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Choo, Ki-hun ,  Lee, Jae-won ,  Kim, Jeong-su ,  Lee, Ki-seung

IPC分类号： G10L15/04

CPC分类号： G10L15/04

摘要： A method of setting an optimum-partitioned classified neural network and a method and apparatus for automatic labeling using an optimum-partitioned classified neural network are provided. The method of automatic labeling using an optimum-partitioned classified neural network comprises (a) searching for neural networks having minimum errors with respect to a number of L phoneme combinations from a number of K neural network combinations generated at an initial stage or updated, updating weights during learning of the K neural networks by K phoneme combination groups searched with the same neural networks, and composing an optimum-partitioned classified neural network combination using the K neural networks of which a total error sum has converged; and (b) tuning a phoneme boundary of a first label file by using the phoneme combination group classification result and the optimum-partitioned classified neural network combination, and generating a final label file reflecting the tuning result.

公开(公告)号：EP1453037A2

公开(公告)日：2004-09-01

申请号：EP04251145.1

申请日：2004-02-27

申请人： Samsung Electronics Co., Ltd.

发明人： Choo, Ki-hun ,  Lee, Jae-won ,  Kim, Jeong-su ,  Lee, Ki-seung

IPC分类号： G10L15/04

CPC分类号： G10L15/04

摘要： A method of setting an optimum-partitioned classified neural network and a method and apparatus for automatic labeling using an optimum-partitioned classified neural network are provided. The method of automatic labeling using an optimum-partitioned classified neural network comprises (a) searching for neural networks having minimum errors with respect to a number of L phoneme combinations from a number of K neural network combinations generated at an initial stage or updated, updating weights during learning of the K neural networks by K phoneme combination groups searched with the same neural networks, and composing an optimum-partitioned classified neural network combination using the K neural networks of which a total error sum has converged; and (b) tuning a phoneme boundary of a first label file by using the phoneme combination group classification result and the optimum-partitioned classified neural network combination, and generating a final label file reflecting the tuning result.

摘要翻译： 设置在最佳分区分类的神经网络，并用于使用在最佳分区分类的神经网络的自动贴标签的方法和装置的设置的方法。 自动贴标签的使用在最佳分区归类神经网络包括方法（a）搜索具有相对于误差最小的神经网络的数量L音素组合的从许多在初始阶段或更新生成的K个神经网络的组合，更新 用K音素组合组学习K个神经网络的权重过程中搜索用相同的神经网络，并在构成最佳分区分类使用的是哪个的K个神经网络总误差总和已经收敛神经网络组合; 和（b）通过使用音素组组合的分类结果和最佳分区分类的神经网络组合，并且生成最终标签文件反映调谐结果调谐的第一标签文件的音素边界。