公开(公告)号：US20100114556A1

公开(公告)日：2010-05-06

申请号：US12609647

申请日：2009-10-30

申请人： Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang ,  Shi Lei Zhang

发明人： Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang ,  Shi Lei Zhang

IPC分类号： G06F17/28

CPC分类号： G06F17/289 ,  G06F17/27 ,  G10L13/033 ,  G10L13/08 ,  G10L21/00

摘要： A method and apparatus for speech translation. The method includes: receiving a source speech; extracting non-text information in the source speech; translating the source speech into a target speech; and adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech. The apparatus includes: a receiving module for receiving source speech; an extracting module for extracting non-text information in the source speech; a translation module for translating the source speech into a target speech; and an adjusting module for adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech.

摘要翻译： 一种用于语音翻译的方法和装置。 该方法包括：接收源语音; 提取源语音中的非文本信息; 将源语言翻译成目标语音; 以及根据提取的非文本信息调整翻译的目标语音，使得目标语音保留源语音中的非文本信息。 该装置包括：用于接收源语音的接收模块; 提取模块，用于提取源语音中的非文本信息; 用于将源语音翻译成目标语音的翻译模块; 以及调整模块，用于根据提取的非文本信息调整翻译的目标语音，使得目标语音保留源语音中的非文本信息。

公开(公告)号：US09342509B2

公开(公告)日：2016-05-17

申请号：US12609647

申请日：2009-10-30

申请人： Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang ,  Shi Lei Zhang

发明人： Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang ,  Shi Lei Zhang

IPC分类号： G06F17/27 ,  G10L13/033 ,  G10L13/08 ,  G10L21/00 ,  G06F17/28

CPC分类号： G06F17/289 ,  G06F17/27 ,  G10L13/033 ,  G10L13/08 ,  G10L21/00

摘要： A method and apparatus for speech translation. The method includes: receiving a source speech; extracting non-text information in the source speech; translating the source speech into a target speech; and adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech. The apparatus includes: a receiving module for receiving source speech; an extracting module for extracting non-text information in the source speech; a translation module for translating the source speech into a target speech; and an adjusting module for adjusting the translated target speech according to the extracted non-text information so that the target speech preserves the non-text information in the source speech.

摘要翻译： 一种用于语音翻译的方法和装置。 该方法包括：接收源语音; 提取源语音中的非文本信息; 将源语言翻译成目标语音; 以及根据提取的非文本信息调整翻译的目标语音，使得目标语音保留源语音中的非文本信息。 该装置包括：用于接收源语音的接收模块; 提取模块，用于提取源语音中的非文本信息; 用于将源语音翻译成目标语音的翻译模块; 以及调整模块，用于根据提取的非文本信息调整翻译的目标语音，使得目标语音保留源语音中的非文本信息。

公开(公告)号：US08280739B2

公开(公告)日：2012-10-02

申请号：US12061645

申请日：2008-04-03

申请人： Dan Ning Jiang ,  Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang

发明人： Dan Ning Jiang ,  Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang

IPC分类号： G10L13/00

CPC分类号： G10L13/04 ,  G10L25/48

摘要： The present invention provides a speech analysis method comprising steps of obtaining a speech signal and a corresponding DEGG/EGG signal; regarding the speech signal as the output of a vocal tract filter in a source-filter model taking the DEGG/EGG signal as the input; and estimating the features of the vocal tract filter from the speech signal as the output and the DEGG/EGG signal as the input, wherein the features of the vocal tract filter are expressed by the state vectors of the vocal tract filter at selected time points, and the step of estimating is performed using Kalman filtering.

摘要翻译： 本发明提供一种语音分析方法，包括获得语音信号和对应的DEGG / EGG信号的步骤; 将语音信号作为采用DEGG / EGG信号作为输入的源滤波器模型中的声道滤波器的输出; 并从语音信号作为输出和DEGG / EGG信号作为输入来估计声道滤波器的特征，其中声道滤波器的特征由选择的时间点处的声道滤波器的状态矢量表示， 并且使用卡尔曼滤波执行估计步骤。

公开(公告)号：US09025736B2

公开(公告)日：2015-05-05

申请号：US12025535

申请日：2008-02-04

申请人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： H04M1/64 ,  H04M3/00 ,  H04M3/51 ,  H04M3/42

CPC分类号： H04M3/4936 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/2011

摘要： A method, information processing system, and computer program storage product for automatically generating auditory archives in a customer service environment are disclosed. A communication link with an end user is established. An information form is retrieved. The information form includes at least a category choice information set and at least one audio recoding information set. The end user is prompted to answer a set of questions based on information in the information form. A data set associated with each answer to each question in the set of questions given by the end user is stored. The data is stored under a set of fields corresponding to a question. Each data set stored under the set of fields for each question in the set of questions are combined with each other. An audio archive file is generated including the data sets that have been combined.

公开(公告)号：US08234110B2

公开(公告)日：2012-07-31

申请号：US12240148

申请日：2008-09-29

申请人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： G10L19/06

CPC分类号： G10L21/00 ,  G10L2021/0135

摘要： A method, system and computer program product for voice conversion. The method includes performing speech analysis on the speech of a source speaker to achieve speech information; performing spectral conversion based on said speech information, to at least achieve a first spectrum similar to the speech of a target speaker; performing unit selection on the speech of said target speaker at least using said first spectrum as a target; replacing at least part of said first spectrum with the spectrum of the selected target speaker's speech unit; and performing speech reconstruction at least based on the replaced spectrum.

摘要翻译： 用于语音转换的方法，系统和计算机程序产品。 该方法包括对源扬声器的语音执行语音分析以实现语音信息; 基于所述语音信息执行频谱转换，至少实现与目标说话者的语音相似的第一频谱; 至少使用所述第一光谱作为目标对所述目标说话者的语音进行单元选择; 用所选择的目标说话者的语音单元的频谱代替所述第一频谱的至少一部分; 并至少基于所替换的频谱执行语音重建。

公开(公告)号：US20090089063A1

公开(公告)日：2009-04-02

申请号：US12240148

申请日：2008-09-29

申请人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： Fan Ping Meng ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： G10L21/00

CPC分类号： G10L21/00 ,  G10L2021/0135

摘要： A method, system and computer program product for voice conversion. The method includes performing speech analysis on the speech of a source speaker to achieve speech information; performing spectral conversion based on said speech information, to at least achieve a first spectrum similar to the speech of a target speaker; performing unit selection on the speech of said target speaker at least using said first spectrum as a target; replacing at least part of said first spectrum with the spectrum of the selected target speaker's speech unit; and performing speech reconstruction at least based on the replaced spectrum.

摘要翻译： 用于语音转换的方法，系统和计算机程序产品。 该方法包括对源扬声器的语音执行语音分析以实现语音信息; 基于所述语音信息执行频谱转换，至少实现与目标说话者的语音相似的第一频谱; 至少使用所述第一光谱作为目标对所述目标说话者的语音进行单元选择; 用所选择的目标说话者的语音单元的频谱代替所述第一频谱的至少一部分; 并至少基于所替换的频谱执行语音重建。

公开(公告)号：US20080288258A1

公开(公告)日：2008-11-20

申请号：US12061645

申请日：2008-04-03

申请人： Dan Ning Jiang ,  Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang

发明人： Dan Ning Jiang ,  Fan Ping Meng ,  Yong Qin ,  Zhi Wei Shuang

IPC分类号： G10L13/00

CPC分类号： G10L13/04 ,  G10L25/48

摘要： The present invention provides a speech analysis method comprising steps of obtaining a speech signal and a corresponding DEGG/EGG signal; regarding the speech signal as the output of a vocal tract filter in a source-filter model taking the DEGG/EGG signal as the input; and estimating the features of the vocal tract filter from the speech signal as the output and the DEGG/EGG signal as the input, wherein the features of the vocal tract filter are expressed by the state vectors of the vocal tract filter at selected time points, and the step of estimating is performed using Kalman filtering.

摘要翻译： 本发明提供一种语音分析方法，包括获得语音信号和对应的DEGG / EGG信号的步骤; 将语音信号作为采用DEGG / EGG信号作为输入的源滤波器模型中的声道滤波器的输出; 并从语音信号作为输出和DEGG / EGG信号作为输入来估计声道滤波器的特征，其中声道滤波器的特征由选择的时间点处的声道滤波器的状态矢量表示， 并且使用卡尔曼滤波执行估计步骤。

公开(公告)号：US20080187109A1

公开(公告)日：2008-08-07

申请号：US12025535

申请日：2008-02-04

申请人： FAN PING MENG ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： FAN PING MENG ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： H04M1/64

CPC分类号： H04M3/4936 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/2011

摘要： A method, information processing system, and computer program storage product for automatically generating auditory archives in a customer service environment are disclosed. A communication link with an end user is established. An information form is retrieved. The information form includes at least a category choice information set and at least one audio recoding information set. The end user is prompted to answer a set of questions based on information in the information form. A data set associated with each answer to each question in the set of questions given by the end user is stored. The data is stored under a set of fields corresponding to a question. Each data set stored under the set of fields for each question in the set of questions are combined with each other. An audio archive file is generated including the data sets that have been combined.

摘要翻译： 公开了一种在客户服务环境中自动生成听觉档案的方法，信息处理系统和计算机程序存储产品。 建立与终端用户的通信链路。 检索一个信息表单。 所述信息表格至少包括类别选择信息集和至少一个音频重新编码信息集。 提示最终用户基于信息表单中的信息来回答一组问题。 存储与最终用户给出的一组问题中的每个问题的每个答案相关联的数据集。 数据存储在与问题相对应的一组字段下。 存储在该组问题中的每个问题的字段集下的每个数据集彼此组合。 生成包括已组合的数据集的音频档案文件。

公开(公告)号：US08170878B2

公开(公告)日：2012-05-01

申请号：US12181553

申请日：2008-07-29

申请人： Yi Liu ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： Yi Liu ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： G10L19/00

CPC分类号： G10L13/08 ,  G10L13/033 ,  G10L2021/0135

摘要： The invention proposes a method and apparatus for significantly improving the quality of voice morphing and guaranteeing the similarity of converted voice. The invention sets several standard speakers in a TTS database, and selects the voices of different standard speakers for speech synthesis according to different roles, wherein the voice of the selected standard speaker is similar to the original role to a certain extent. Then the invention further performs voice morphing on the standard voice similar to the original voice to a certain extent, in order to accurately mimic the voice of the original speaker, so as to make the converted voice closer to the original voice features while guaranteeing the similarity.

摘要翻译： 本发明提出了一种显着提高语音变形质量并保证转换语音相似性的方法和装置。 本发明在TTS数据库中设置几个标准扬声器，并根据不同的角色选择不同标准扬声器的语音合成语音，其中所选标准扬声器的声音在一定程度上与原始角色相似。 然后本发明在一定程度上进一步对与原始语音相似的标准语音进行声音变形，以便准确地模拟原始扬声器的声音，以便使转换的语音更接近原始语音特征，同时保证相似性 。

公开(公告)号：US20090037179A1

公开(公告)日：2009-02-05

申请号：US12181553

申请日：2008-07-29

申请人： Yi Liu ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

发明人： Yi Liu ,  Yong Qin ,  Qin Shi ,  Zhi Wei Shuang

IPC分类号： G10L13/08

CPC分类号： G10L13/08 ,  G10L13/033 ,  G10L2021/0135

摘要： The invention proposes a method and apparatus for significantly improving the quality of voice morphing and guaranteeing the similarity of converted voice. The invention sets several standard speakers in a TTS database, and selects the voices of different standard speakers for speech synthesis according to different roles, wherein the voice of the selected standard speaker is similar to the original role to a certain extent. Then the invention further performs voice morphing on the standard voice similar to the original voice to a certain extent, in order to accurately mimic the voice of the original speaker, so as to make the converted voice closer to the original voice features while guaranteeing the similarity.

摘要翻译： 本发明提出了一种显着提高语音变形质量并保证转换语音相似性的方法和装置。 本发明在TTS数据库中设置几个标准扬声器，并根据不同的角色选择不同标准扬声器的语音合成语音，其中所选标准扬声器的声音在一定程度上与原始角色相似。 然后本发明在一定程度上进一步对与原始语音相似的标准语音进行声音变形，以便准确地模拟原始扬声器的声音，以便使转换的语音更接近原始语音特征，同时保证相似性 。