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

WO2007116253A3 METHOD, APPARATUS, MOBILE TERMINAL AND COMPUTER PROGRAM PRODUCT FOR PROVIDING EFFICIENT EVALUATION OF FEATURE TRANSFORMATION 审中-公开
标题翻译：用于对特征变换进行有效评估的方法，装置，移动终端和计算机程序产品
公开(公告)号：WO2007116253A3
公开(公告)日：2007-12-21
申请号：PCT/IB2007000580
申请日：2007-03-09
申请人： NOKIA CORP , NOKIA INC , TIAN JILEI , NURMINEN JANI K , POPA VICTOR
发明人： TIAN JILEI , NURMINEN JANI K , POPA VICTOR
IPC分类号： G10L13/04 , G10L17/00
CPC分类号： G10L21/00 , G10L13/033 , G10L2021/0135
摘要： An apparatus for providing efficient evaluation of feature transformation includes a training module and a transformation module. The training module is configured to train a Gaussian mixture model (GMM) using training source data and training target data. The transformation module is in communication with the training module. The transformation module is configured to produce a conversion function in response to the training of the GMM. The training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM.
摘要翻译：一种用于提供特征变换的有效评估的装置包括训练模块和变换模块。训练模块被配置为使用训练源数据和训练目标数据训练高斯混合模型（GMM）。转换模块与培训模块进行通信。转换模块被配置为响应于GMM的训练产生转换函数。训练模块还被配置为通过计算GMM的轨迹测量来在使用转换函数之前确定转换函数的质量。

2. 发明申请

WO2007046060A3 COMPRESSION AND DECOMPRESSION OF DATA VECTORS 审中-公开
标题翻译：数据向量的压缩与解压缩
公开(公告)号：WO2007046060A3
公开(公告)日：2007-08-16
申请号：PCT/IB2006053836
申请日：2006-10-18
申请人： NOKIA CORP , NURMINEN JANI K
发明人： NURMINEN JANI K
IPC分类号： H03M7/40 , G10L19/02
CPC分类号： H03M7/40
摘要： For an enhanced sequential compression of data vectors in a respective compression pass, a current data vector is mapped to at least one current code vector of at least one codebook in at least one quantization stage. The at least one codebook is reordered taking account of at least one intermediate result from the current compression pass and at least one intermediate result from a preceding compression pass. At least one codebook index that is associated in the at least one reordered codebook to the at least one current code vector is then provided for further use. For a decompression of compressed data vectors represented by such codebook indices, at least one codebook index is mapped to at least one code vector of at least one equally reordered codebook.
摘要翻译：对于相应压缩过程中的数据向量的增强的顺序压缩，当前数据向量被映射到至少一个量化阶段中的至少一个码本的至少一个当前码向量。考虑到来自当前压缩过程的至少一个中间结果和来自先前压缩过程的至少一个中间结果，对至少一个码本进行重新排序。随后提供至少一个在至少一个重排序码本中与至少一个当前码向量相关联的码本索引以供进一步使用。为了对由这样的码本索引表示的压缩数据向量进行解压缩，将至少一个码本索引映射到至少一个同等重排序码本的至少一个码向量。

3. 发明申请

WO2008122863A1 VOICE ACTIVITY DETECTION AND DATA COLLECTION FOR VOICE CONVERSION TRAINING 审中-公开
标题翻译：语音活动检测和数据收集语音转换训练
公开(公告)号：WO2008122863A1
公开(公告)日：2008-10-16
申请号：PCT/IB2008/000807
申请日：2008-03-28
申请人： NOKIA CORPORATION , NOKIA, INC , NURMINEN, Jani K. , POPA, Victor , HELANDER, Elina , TIAN, Jilei
发明人： NURMINEN, Jani K. , POPA, Victor , HELANDER, Elina , TIAN, Jilei
IPC分类号： G10L11/02 , G10L15/04
CPC分类号： G10L21/028 , G10L15/04 , G10L25/78 , G10L2021/0135
摘要： It may be desirable to provide a way to collect high quality speech training data without undue burden to the user. Speech training data may be collected during normal usage of a device. In this way, the collection of speech training data may be effectively transparent to the user, without the need for a distinct collection mode from the user's point of view. For example, where the devices is or includes a phone (such as a cellular phone), when the user makes or receives a phone call to/from another party, speech training data may be automatically collected from one or both of the parties during the phone call.
摘要翻译：可能需要提供一种收集高质量语音训练数据的方式，而不会对用户造成不必要的负担。在设备的正常使用期间可以收集语音训练数据。以这种方式，语音训练数据的收集对于用户来说可能是有效的透明的，而不需要用户的观点的不同的收集模式。例如，当设备是或包括电话（例如蜂窝电话）时，当用户向/从另一方进行或接收电话呼叫时，可以在一方或两方当中自动收集语音训练数据电话。

4. 发明申请

WO2007046060A2 COMPRESSION AND DECOMPRESSION OF DATA VECTORS 审中-公开
标题翻译：数据向量的压缩和分解
公开(公告)号：WO2007046060A2
公开(公告)日：2007-04-26
申请号：PCT/IB2006/053836
申请日：2006-10-18
申请人： NOKIA CORPORATION , NURMINEN, Jani K.
发明人： NURMINEN, Jani K.
CPC分类号： H03M7/40 , G10L2019/0005
摘要： For an enhanced sequential compression of data vectors in a respective compression pass, a current data vector is mapped to at least one current code vector of at least one codebook in at least one quantization stage. The at least one codebook is reordered taking account of at least one intermediate result from the current compression pass and at least one intermediate result from a preceding compression pass. At least one codebook index that is associated in the at least one reordered codebook to the at least one current code vector is then provided for further use. For a decompression of compressed data vectors represented by such codebook indices, at least one codebook index is mapped to at least one code vector of at least one equally reordered codebook.
摘要翻译：为了在相应的压缩过程中对数据向量进行增强的顺序压缩，将当前数据矢量映射到至少一个量化级中的至少一个码本的至少一个当前码矢量。考虑到来自当前压缩通过的至少一个中间结果和来自前一个压缩通过的至少一个中间结果，重新排序至少一个码本。然后提供至少一个与至少一个重排序码本相关联的至少一个当前码矢量的码本索引用于进一步使用。对于由这样的码本索引表示的压缩数据向量的解压缩，至少一个码本索引被映射到至少一个同样重排的码本的至少一个码矢量。

5. 发明申请

WO2008038082A2 PROSODY CONVERSION 审中-公开
标题翻译： PROSODY转换
公开(公告)号：WO2008038082A2
公开(公告)日：2008-04-03
申请号：PCT/IB2007/002690
申请日：2007-09-17
申请人： NOKIA CORPORATION , NOKIA, INC. , NURMINEN, Jani K. , HELANDER, Elina
发明人： NURMINEN, Jani K. , HELANDER, Elina
IPC分类号： G10L19/04 , G10L13/02
CPC分类号： G10L21/00 , G10L13/04 , G10L2021/0135
摘要： A contour for a syllable (or other speech segment) in a voice undergoing conversion is transformed. The transform of that contour is then used to identify one or more source syllable transforms in a codebook. Information regarding the context and/or linguistic features of the contour being converted can also be compared to similar information in the codebook when identifying an appropriate source transform. Once a codebook source transform is selected, an inverse transformation is performed on a corresponding codebook target transform to yield an output contour. The corresponding codebook target transform represents a target voice version of the same syllable represented by the selected codebook source transform. The output contour may be further processed to improve conversion quality.
摘要翻译：正在进行转换的语音中的音节（或其他语音段）的轮廓被转换。然后，该轮廓的变换用于识别码本中的一个或多个源音节转换。关于正在转换的轮廓的上下文和/或语言特征的信息也可以在识别适当的源变换时与码本中的类似信息进行比较。一旦选择了码本源变换，就对相应的码本目标变换进行逆变换以产生输出轮廓。相应的码本目标变换表示由所选码本源变换表示的相同音节的目标语音版本。可以进一步处理输出轮廓以提高转换质量。

6. 发明申请

WO2008038082A3 PROSODY CONVERSION 审中-公开
标题翻译： PROSODY转换
公开(公告)号：WO2008038082A3
公开(公告)日：2008-09-04
申请号：PCT/IB2007002690
申请日：2007-09-17
申请人： NOKIA CORP , NOKIA INC , NURMINEN JANI K , HELANDER ELINA
发明人： NURMINEN JANI K , HELANDER ELINA
IPC分类号： G10L21/00 , G10L13/02 , G10L19/04
CPC分类号： G10L21/00 , G10L13/04 , G10L2021/0135
摘要： A contour for a syllable (or other speech segment) in a voice undergoing conversion is transformed. The transform of that contour is then used to identify one or more source syllable transforms in a codebook. Information regarding the context and/or linguistic features of the contour being converted can also be compared to similar information in the codebook when identifying an appropriate source transform. Once a codebook source transform is selected, an inverse transformation is performed on a corresponding codebook target transform to yield an output contour. The corresponding codebook target transform represents a target voice version of the same syllable represented by the selected codebook source transform. The output contour may be further processed to improve conversion quality.
摘要翻译：变换正在进行转换的语音中的音节（或其他语音片段）的轮廓。该轮廓的变换然后用于识别码本中的一个或多个源音节变换。当识别适当的源变换时，关于被变换的轮廓的上下文和/或语言特征的信息也可以与码本中的类似信息进行比较。一旦选择了码本源变换，就对相应的码本目标变换执行逆变换以产生输出轮廓。对应的码本目标变换表示由所选择的码本源变换表示的相同音节的目标语音版本。输出轮廓可以被进一步处理以提高转换质量。

7. 发明申请

WO2007116253A2 METHOD, APPARATUS, MOBILE TERMINAL AND COMPUTER PROGRAM PRODUCT FOR PROVIDING EFFICIENT EVALUATION OF FEATURE TRANSFORMATION 审中-公开
标题翻译：方法，装置，移动终端和计算机程序产品，用于提供特征转换的有效评估
公开(公告)号：WO2007116253A2
公开(公告)日：2007-10-18
申请号：PCT/IB2007/000580
申请日：2007-03-09
申请人： NOKIA CORPORATION , NOKIA, INC. , TIAN, Jilei , NURMINEN, Jani, K. , POPA, Victor
发明人： TIAN, Jilei , NURMINEN, Jani, K. , POPA, Victor
IPC分类号： G10L13/04 , G10L17/00
CPC分类号： G10L21/00 , G10L13/033 , G10L2021/0135
摘要： An apparatus for providing efficient evaluation of feature transformation includes a training module and a transformation module. The training module is configured to train a Gaussian mixture model (GMM) using training source data and training target data. The transformation module is in communication with the training module. The transformation module is configured to produce a conversion function in response to the training of the GMM. The training module is further configured to determine a quality of the conversion function prior to use of the conversion function by calculating a trace measurement of the GMM.
摘要翻译：用于提供特征变换的有效评估的装置包括训练模块和变换模块。训练模块被配置为使用训练源数据和训练目标数据训练高斯混合模型（GMM）。变换模块与训练模块通信。转换模块被配置为响应于GMM的训练而产生转换功能。训练模块还被配置为通过计算GMM的跟踪测量来确定在使用转换功能之前的转换功能的质量。

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