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. 发明授权

US07478036B2 Method and system for automatically extracting new word 有权
公开(公告)号：US07478036B2
公开(公告)日：2009-01-13
申请号：US09944332
申请日：2001-08-30
申请人： Liqin Shen , Qin Shi , Haixin Chai
发明人： Liqin Shen , Qin Shi , Haixin Chai
IPC分类号： G06F17/27
CPC分类号： G10L15/063 , G10L15/183
摘要： A method of and system for automatically extracting new words are provided. The method and system are highly efficient for automatically extracting new words from a mass amount of cleaned corpus.

2. 发明申请

US20070233494A1 METHOD AND SYSTEM FOR GENERATING SOUND EFFECTS INTERACTIVELY 审中-公开
标题翻译：产生声音效果的方法和系统互动
公开(公告)号：US20070233494A1
公开(公告)日：2007-10-04
申请号：US11691511
申请日：2007-03-27
申请人： Liqin Shen , Hai Ping Li , Qin Shi , Zhiwei Shuang
发明人： Liqin Shen , Hai Ping Li , Qin Shi , Zhiwei Shuang
IPC分类号： G10L13/08
CPC分类号： G10H1/0091 , G10H2240/145 , G10H2250/315 , G10L13/033
摘要： The invention provides a method and system for generating sound effects interactively. The method provides a plurality of sound effect tags to a user, wherein each of the plurality of sound effects corresponds to a specific sound effect object. The sound effect object includes a seed sound representing a predefined audio file and a sound effect action representing an operation on sound. Then the user selects at least one of the sound effect tags for a whole source sound or at least a piece of the source sound. The method edits the source sound by using the selected sound effect tags to form a sound effect expression, interprets the sound effect expression to determine the operations corresponding to respective sound effect tags in the sound effect expression and the execution order of the operations, and executes the operations in said order to output a sound with the sound effects. The method of the invention enables a user to perform sound effect editing on sound in real time and dynamically, thus providing more customized sound effects.
摘要翻译：本发明提供了一种用于交互地产生声音效果的方法和系统。该方法向用户提供多个声音效果标签，其中多个声音效果中的每一个对应于特定的声音效果对象。声音对象包括表示预定音频文件的种子声音和表示声音操作的声音效果动作。然后，用户为整个源声音或至少一段源声音选择至少一个声音效果标签。该方法通过使用所选择的声音效果标签来形成声音效果表达式，解释声音效果表达式以确定与声音效果表达式中的各个声音效果标签相对应的操作和操作的执行顺序，并执行按照所述顺序的操作输出具有声音效果的声音。本发明的方法使得用户能够实时地和动态地对声音执行声音效果编辑，从而提供更多定制的声音效果。

3. 发明申请

US20070033049A1 Method and system for generating synthesized speech based on human recording 有权
标题翻译：基于人类记录生成合成语音的方法和系统
公开(公告)号：US20070033049A1
公开(公告)日：2007-02-08
申请号：US11475820
申请日：2006-06-27
申请人： Yong Qin , Liqin Shen , Wei Zhang , Weibin Zhu
发明人： Yong Qin , Liqin Shen , Wei Zhang , Weibin Zhu
IPC分类号： G10L13/08
CPC分类号： G10L13/04
摘要： A method and system that incorporates human recording with a TTS system to generate synthesized speech with high quality by searching over a database of pre-recorded utterances to select an utterance best matching text content to be synthesized into speech; dividing the best-matched utterance into a plurality of segments to generate remaining segments that are the same as corresponding parts of the text content and difference segments that are different from corresponding parts of the text content; synthesizing speech for the parts of the text content corresponding to the difference segments; and splicing the synthesized speech segments with the remaining segments of the best-matched utterance.
摘要翻译：一种将人类记录与TTS系统相结合的方法和系统，通过在数据库上搜索预先录制的话语来选择要合成语音的最佳匹配文本内容，从而产生高质量的合成语音; 将最佳匹配的话语划分成多个段以产生与文本内容的对应部分和与文本内容的对应部分不同的差异段的剩余段; 对与差分片段相对应的文本内容的部分合成语音; 以及将合成的语音片段与最佳匹配的话语的剩余片段拼接。

4. 发明授权

US08401861B2 Generating a frequency warping function based on phoneme and context 有权
标题翻译：基于音素和语境生成频率扭曲函数
公开(公告)号：US08401861B2
公开(公告)日：2013-03-19
申请号：US11654447
申请日：2007-01-17
申请人： Shuang Zhi Wei , Raimo Bakis , Ellen Marie Eide , Liqin Shen
发明人： Shuang Zhi Wei , Raimo Bakis , Ellen Marie Eide , Liqin Shen
IPC分类号： G10L21/00 , G10L13/06
CPC分类号： G10L15/07 , G10L2021/0135
摘要： A method for generating a frequency warping function comprising preparing the training speech of a source and a target speaker; performing frame alignment on the training speech of the speakers; selecting aligned frames from the frame-aligned training speech of the speakers; extracting corresponding sets of formant parameters from the selected aligned frames; and generating a frequency warping function based on the corresponding sets of formant parameters. The step of selecting aligned frames preferably selects a pair of aligned frames in the middle of the same or similar frame-aligned phonemes with the same or similar contexts in the speech of the source speaker and target speaker. The step of generating a frequency warping function preferably uses the various pairs of corresponding formant parameters in the corresponding sets of formant parameters as key positions in a piecewise linear frequency warping function to generate the frequency warping function.
摘要翻译：一种用于产生频率扭曲函数的方法，包括准备源和目标说话者的训练语音; 对演讲者的训练语音进行框架对齐; 从扬声器的帧对齐训练语音中选择对准的帧; 从所选择的对齐的帧中提取相应的共振峰参数集合; 以及基于相应的共振峰参数集合生成频率扭曲函数。选择对准的帧的步骤优选地在源扬声器和目标扬声器的语音中使用相同或相似的上下文在相同或相似的帧对准音素的中间选择一对对齐的帧。产生频率扭曲函数的步骤优选地使用相应的共振峰参数集合中的各种相应的共振峰参数作为分段线性频率扭曲函数中的关键位置来产生频率扭曲函数。

5. 发明授权

US07899672B2 Method and system for generating synthesized speech based on human recording 有权
标题翻译：基于人类记录生成合成语音的方法和系统
公开(公告)号：US07899672B2
公开(公告)日：2011-03-01
申请号：US11475820
申请日：2006-06-27
申请人： Yong Qin , Liqin Shen , Wei Zhang , Weibin Zhu
发明人： Yong Qin , Liqin Shen , Wei Zhang , Weibin Zhu
IPC分类号： G10L13/08 , G10L13/00
CPC分类号： G10L13/04
摘要： A method and system that incorporates human recording with a TTS system to generate synthesized speech with high quality by searching over a database of pre-recorded utterances to select an utterance best matching text content to be synthesized into speech; dividing the best-matched utterance into a plurality of segments to generate remaining segments that are the same as corresponding parts of the text content and difference segments that are different from corresponding parts of the text content; synthesizing speech for the parts of the text content corresponding to the difference segments; and splicing the synthesized speech segments with the remaining segments of the best-matched utterance.
摘要翻译：一种将人类记录与TTS系统相结合的方法和系统，通过在数据库上搜索预先录制的话语来选择要合成语音的最佳匹配文本内容，从而产生高质量的合成语音; 将最佳匹配的话语划分成多个段以产生与文本内容的对应部分和与文本内容的对应部分不同的差异段的剩余段; 对与差分片段相对应的文本内容的部分合成语音; 以及将合成的语音片段与最佳匹配的话语的剩余片段拼接。

6. 发明申请

US20070185715A1 Method and apparatus for generating a frequency warping function and for frequency warping 有权
标题翻译：用于产生频率翘曲功能和频率翘曲的方法和装置
公开(公告)号：US20070185715A1
公开(公告)日：2007-08-09
申请号：US11654447
申请日：2007-01-17
申请人： Shuang Wei , Raimo Bakis , Ellen Eide , Liqin Shen
发明人： Shuang Wei , Raimo Bakis , Ellen Eide , Liqin Shen
IPC分类号： G10L15/04
CPC分类号： G10L15/07 , G10L2021/0135
摘要： A method for generating a frequency warping function comprising preparing the training speech of a source and a target speaker; performing frame alignment on the training speech of the speakers; selecting aligned frames from the frame-aligned training speech of the speakers; extracting corresponding sets of formant parameters from the selected aligned frames; and generating a frequency warping function based on the corresponding sets of formant parameters. The step of selecting aligned frames preferably selects a pair of aligned frames in the middle of the same or similar frame-aligned phonemes with the same or similar contexts in the speech of the source speaker and target speaker. The step of generating a frequency warping function preferably uses the various pairs of corresponding formant parameters in the corresponding sets of formant parameters as key positions in a piecewise linear frequency warping function to generate the frequency warping function.
摘要翻译：一种用于产生频率扭曲函数的方法，包括准备源和目标说话者的训练语音; 对演讲者的训练语音进行框架对齐; 从扬声器的帧对齐训练语音中选择对准的帧; 从所选择的对齐的帧中提取相应的共振峰参数集合; 以及基于相应的共振峰参数集合生成频率扭曲函数。选择对准的帧的步骤优选地在源扬声器和目标扬声器的语音中使用相同或相似的上下文在相同或相似的帧对准音素的中间选择一对对齐的帧。产生频率扭曲函数的步骤优选地使用相应的共振峰参数集合中的各种相应的共振峰参数作为分段线性频率扭曲函数中的关键位置来产生频率扭曲函数。

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