专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20130066631A1 PARAMETRIC SPEECH SYNTHESIS METHOD AND SYSTEM 有权
标题翻译：参数语音合成方法与系统
公开(公告)号：US20130066631A1
公开(公告)日：2013-03-14
申请号：US13640562
申请日：2011-10-27
申请人： Fengliang Wu , Zhenhua Wu
发明人： Fengliang Wu , Zhenhua Wu
IPC分类号： G10L13/00
CPC分类号： G10L13/08 , G10L2015/227
摘要： The present invention provides a parametric speech synthesis method and a parametric speech synthesis system. The method comprises sequentially processing each frame of speech of each phone in a phone sequence of an input text as follows: for a current phone, extracting a corresponding statistic model from a statistic model library and using model parameters of the statistic model that correspond to the current frame of the current phone as rough values of currently predicted speech parameters; according to the rough values and information about a predetermined number of speech frames occurring before the current time point, obtaining smoothed values of the currently predicted speech parameters; according to global mean values and global standard deviation ratios of the speech parameters obtained through statistics, performing global optimization on the smoothed values of the speech parameters to generate necessary speech parameters; and synthesizing the generated speech parameters to obtain a frame of speech synthesized for the current frame of the current phone. With this solution, the capacity of an RAM needed by speech synthesis will not increase with the length of the synthesized speech, and the time length of the synthesized speech is no longer limited by the RAM.
摘要翻译：本发明提供一种参数语音合成方法和参数语音合成系统。该方法包括以如下方式在输入文本的电话序列中顺序处理每个电话的每个帧：对于当前电话，从统计模型库中提取相应的统计模型，并使用对应于该统计模型的统计模型的模型参数当前手机的当前帧作为当前预测的语音参数的粗略值; 根据关于在当前时间点之前发生的预定数量的语音帧的粗略值和信息，获得当前预测的语音参数的平滑值; 根据通过统计获得的语音参数的全局平均值和全局标准偏差比，对语音参数的平滑值进行全局优化以产生必要的语音参数; 以及合成所生成的语音参数以获得为当前电话的当前帧合成的语音帧。利用该解决方案，语音合成所需的RAM的容量不会随着合成语音的长度而增加，并且合成语音的时间长度不再受RAM限制。

2. 发明授权

US08977551B2 Parametric speech synthesis method and system 有权
标题翻译：参数语音合成方法和系统
公开(公告)号：US08977551B2
公开(公告)日：2015-03-10
申请号：US13640562
申请日：2011-10-27
申请人： Fengliang Wu , Zhenhua Wu
发明人： Fengliang Wu , Zhenhua Wu
IPC分类号： G10L13/00 , G10L13/08 , G10L21/00 , G10L15/00 , H04M1/64 , G10L15/22
CPC分类号： G10L13/08 , G10L2015/227
摘要： The present invention provides a parametric speech synthesis method and a parametric speech synthesis system. The method comprises sequentially processing each frame of speech of each phone in a phone sequence of an input text as follows: for a current phone, extracting a corresponding statistic model from a statistic model library and using model parameters of the statistic model that correspond to the current frame of the current phone as rough values of currently predicted speech parameters; according to the rough values and information about a predetermined number of speech frames occurring before the current time point, obtaining smoothed values of the currently predicted speech parameters; according to global mean values and global standard deviation ratios of the speech parameters obtained through statistics, performing global optimization on the smoothed values of the speech parameters to generate necessary speech parameters; and synthesizing the generated speech parameters to obtain a frame of speech synthesized for the current frame of the current phone. With this solution, the capacity of an RAM needed by speech synthesis will not increase with the length of the synthesized speech, and the time length of the synthesized speech is no longer limited by the RAM.
摘要翻译：本发明提供一种参数语音合成方法和参数语音合成系统。该方法包括以如下方式在输入文本的电话序列中顺序处理每个电话的每个帧：对于当前电话，从统计模型库中提取相应的统计模型，并使用对应于该统计模型的统计模型的模型参数当前手机的当前帧作为当前预测的语音参数的粗略值; 根据关于在当前时间点之前发生的预定数量的语音帧的粗略值和信息，获得当前预测的语音参数的平滑值; 根据通过统计获得的语音参数的全局平均值和全局标准偏差比，对语音参数的平滑值执行全局优化以产生必要的语音参数; 以及合成所生成的语音参数以获得为当前电话的当前帧合成的语音帧。利用该解决方案，语音合成所需的RAM的容量不会随着合成语音的长度而增加，并且合成语音的时间长度不再受RAM限制。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式