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

WO2014207752A1 AUTHENTICATING USER BY CORRELATING SPEECH AND CORRESPONDING LIP SHAPE 审中-公开
标题翻译：通过相关语音和相关的LIP形状来认证用户
公开(公告)号：WO2014207752A1
公开(公告)日：2014-12-31
申请号：PCT/IN2013/000397
申请日：2013-06-27
申请人： HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. , RAMACHANDRULA, Sitaram , RAVISHANKAR, Hariharan
发明人： RAMACHANDRULA, Sitaram , RAVISHANKAR, Hariharan
IPC分类号： G06K9/00
CPC分类号： G06K9/6293 , G06K9/00335 , G06K9/00892 , G06K9/629 , G06T7/73 , G06T2207/10016 , G06T2207/30201 , G10L17/10 , G10L19/038 , G10L25/51 , G10L2019/0005
摘要： Provided is a method of authenticating a user by correlating speech and corresponding lip shape. An audiovisual of a user requesting authentication is captured. The audiovisual is processed to generate a speech vector quantization sequence and a corresponding lip vector quantization sequence of the user. A likelihood of the speech vector quantization sequence and the corresponding lip vector quantization sequence with probability distributions of speech vector quantization code words corresponding to different lip shape vector quantization code words of the user requesting authentication weighed by probabilities of speech and lip vector quantization indices of the user requesting authentication is evaluated. If upon evaluation, a likelihood of the user requesting authentication being an authentic user is more than a predefined threshold, the user is authenticated.
摘要翻译：提供了通过将语音和对应的唇形状相关联来认证用户的方法。捕获请求认证的用户的视听。视听被处理以产生用户的语音矢量量化序列和相应的唇矢量量化序列。语音矢量量化序列的可能性和对应于用户请求认证的不同唇形矢量量化码字的语音矢量量化码字的概率分布的相应唇矢量量化序列被语音和嘴唇矢量量化索引的概率加权评估用户请求认证。如果在评估时，用户请求认证是可信用户的可能性大于预定阈值，则认证用户。

2. 发明申请

WO2012101483A1 CODING THROUGH COMBINATION OF CODE VECTORS 审中-公开
标题翻译：通过代码矢量的组合进行编码
公开(公告)号：WO2012101483A1
公开(公告)日：2012-08-02
申请号：PCT/IB2011/050377
申请日：2011-01-28
申请人： NOKIA CORPORATION , VASILACHE, Adriana , LAAKSONEN, Lasse , RAMO, Anssi , TAMMI, Mikko
发明人： VASILACHE, Adriana , LAAKSONEN, Lasse , RAMO, Anssi , TAMMI, Mikko
IPC分类号： G10L19/00 , G06T9/00 , H03M7/30
CPC分类号： G10L19/038 , G10L19/07 , G10L19/24 , G10L2019/0005 , H03M7/3082 , H04N19/94
摘要： It is inter alia disclosed to determine a single code vector index based on combining at least two code vector indexes, each code vector index being associated with a code vector of a respective codebook.
摘要翻译：公开的是基于组合至少两个码向量索引来确定单个码矢量索引，每个码矢量索引与相应码本的码矢量相关联。

3. 发明申请

WO2011126340A3 METHOD AND APPARATUS FOR PROCESSING AN AUDIO SIGNAL 审中-公开
标题翻译：用于处理音频信号的方法和设备
公开(公告)号：WO2011126340A3
公开(公告)日：2011-12-15
申请号：PCT/KR2011002487
申请日：2011-04-08
申请人： LG ELECTRONICS INC , JEONG GYU HYEOK , JEON HYE JEONG , LEE BYUNG SUK , LEE CHANG HEON
发明人： JEONG GYU HYEOK , JEON HYE JEONG , LEE BYUNG SUK , LEE CHANG HEON
IPC分类号： G10L19/12 , G10L19/02 , G10L19/038 , G10L19/04
CPC分类号： G10L19/008 , G10L19/038 , G10L19/04 , G10L19/06 , G10L2019/0005
摘要： The present invention relates to a method for processing an audio signal, comprising the following steps: performing a linear predictive analysis on the current frame of an audio signal so as to generate a first target vector, which is a target vector of a first stage, on the basis of a plurality of linear prediction transform coefficients; performing vector quantization on the first target vector so as to acquire a predetermined number of first temporary candidate code vectors of the first stage; calculating first temporary candidate errors, which are errors between the first temporary candidate code vectors and the first target vector; and determining a first number, which is the number of the first candidate code vectors, on the basis of the first temporary candidate errors, and acquiring first final candidate code vectors in the same amount as the first number.
摘要翻译：本发明涉及一种音频信号的处理方法，包括以下步骤：对音频信号的当前帧进行线性预测分析，生成第一阶段的目标矢量即第一目标矢量，基于多个线性预测变换系数; 对第一目标矢量执行矢量量化以获取第一级的预定数量的第一临时候选码矢量; 计算作为所述第一临时候选码矢量与所述第一目标矢量之间的误差的第一临时候选误差; 以及基于第一临时候选误差确定作为第一候选码矢量的数量的第一数目，并且获取与第一数目相同量的第一最终候选码矢量。

4. 发明申请

WO2010092827A1 ベクトル量子化装置、ベクトル逆量子化装置、およびこれらの方法审中-公开
标题翻译：矢量量化装置，矢量反相量化装置及其方法
公开(公告)号：WO2010092827A1
公开(公告)日：2010-08-19
申请号：PCT/JP2010/000881
申请日：2010-02-12
申请人：パナソニック株式会社 , 佐藤薫 , 森井利幸
发明人：佐藤薫 , 森井利幸
IPC分类号： H03M7/30 , G10L19/06 , G10L19/14
CPC分类号： G10L19/038 , G10L19/07 , G10L19/12 , G10L19/18 , G10L2019/0005 , H03M7/3082
摘要：　量子化対象ベクトルとの相関を有する特徴の種類によって１段目のベクトル量子化のコードブックを切り替えるベクトル量子化の量子化精度を向上することができるＬＳＰベクトル量子化装置。この装置において、分類器（１０１）は、複数の分類用コードベクトルの中から、量子化対象ベクトルとの相関を有する特徴の種類を示す分類用コードベクトルを選択し、スイッチ（１０２）は、複数の第１コードブックの中から上記種類に対応する第１コードブックを選択し、誤差最小化部（１０５）は、選択された第１コードブックを構成する複数の第１コードベクトルの中から、量子化対象ベクトルに最も近い第１コードベクトルを選択し、行列決定部（１０６）は、複数の行列の中から上記種類に対応する行列を選択し、誤差最小化部（１０５）は、選択された行列を用いて複数の第２コードベクトルの中から、選択された第１コードベクトルと量子化対象ベクトルとの残差ベクトルに最も近いものを選択する。
摘要翻译： LSP向量量化装置能够根据与量化对象矢量具有相关性的特征的类型来切换用于第一级矢量量化的码本的矢量量化中的量化精度。在该装置中，分类器（101）从用于分类的多个代码矢量中选择用于分类的代码矢量，其指示与量化目标矢量具有相关性的特征的类型; 开关（102）从多个第一码本中选择与上述类型对应的第一码本; 误差最小化单元（105）从构成所选择的第一码本的多个第一码矢量中选择最接近量化目标矢量的第一码矢量; 矩阵确定单元（106）从多个矩阵中选择与上述类型对应的矩阵; 并且所述误差最小化单元（105）使用所选择的矩阵从多个第二码矢量中选择最接近所选择的第一码矢量和量化目标矢量之间的残差矢量的矩阵。

5. 发明申请

WO2009114656A1 MULTIMODE CODING OF SPEECH-LIKE AND NON-SPEECH-LIKE SIGNALS 审中-公开
标题翻译：语音类和非语音信号的多模式编码
公开(公告)号：WO2009114656A1
公开(公告)日：2009-09-17
申请号：PCT/US2009/036885
申请日：2009-03-12
申请人： DOLBY LABORATORIES LICENSING CORPORATION , YU, Rongshan , RADHAKRISHNAN, Regunathan , ANDERSEN, Robert, L. , DAVIDSON, Grant, A.
发明人： YU, Rongshan , RADHAKRISHNAN, Regunathan , ANDERSEN, Robert, L. , DAVIDSON, Grant, A.
IPC分类号： G10L19/08 , G10L19/12
CPC分类号： G10L19/18 , G10L19/093 , G10L19/12 , G10L2019/0004 , G10L2019/0005
摘要： The invention relates to the coding of audio signals that may include both speech- like and non-speech-like signal components. It describes methods and apparatus for code excited linear prediction (CELP) audio encoding and decoding that employ linear predictive coding (LPC) synthesis filters controlled by LPC parameters, a plurality of codebooks each having codevectors, at least one codebook providing an excitation more appropriate for non-speech-like signals and at least one codebook providing an excitation more appropriate for speech-like signals, and a plurality of gain factors, each associated with a codebook. The encoding methods and apparatus select from the codebooks codevectors and/or associated gain factors by minimizing a measure of the difference between the audio signal and a reconstruction of the audio signal derived from the codebook excitations. The decoding methods and apparatus generate a reconstructed output signal from the LPC parameters, codevectors, and gain factors.
摘要翻译：本发明涉及音频信号的编码，其可以包括语音类和非语音类信号分量。它描述了采用由LPC参数控制的线性预测编码（LPC）合成滤波器的码激励线性预测（CELP）音频编码和解码的方法和装置，每个具有码矢量的多个码本，提供更适合于非语音类信号和至少一个提供更适合于类似语音的信号的激励的码本，以及多个增益因子，每个与码本相关联。编码方法和装置通过最小化音频信号与从码本激励导出的音频信号的重建之间的差异的度量来从码本代码矢量和/或相关联的增益因子中选择。解码方法和装置从LPC参数，代码矢量和增益因子产生重构的输出信号。

6. 发明申请

WO2008067766A1 矢量量化方法及装置审中-公开
公开(公告)号：WO2008067766A1
公开(公告)日：2008-06-12
申请号：PCT/CN2007/071178
申请日：2007-12-05
申请人：华为技术有限公司 , 李立雄 , 郭利斌 , 张亮 , 张德军 , 吴文海 , 王庭红
发明人：李立雄 , 郭利斌 , 张亮 , 张德军 , 吴文海 , 王庭红
IPC分类号： H03M7/30
CPC分类号： H03M7/3082 , G10L2019/0005 , H04N19/94
摘要： A method for quantizing vector. The method comprises: performing a quantization process on a vector to be quantized by use of N base codebook vectors and modification vectors for each of the base codebook vectors, deriving a base codebook vector and a modification vector used for quantizing the vector to be quantized, N being an integer larger than or equal to 1. According to the present invention, based on the method, a device for quantizing vector is disclosed. According to the embodiment of the present invention, the quantization of an input vector is done by introducing the modification vectors for the base codebook vectors, therefore the memory amount of the base codebook vectors is reduced effectively, and the calculation amount is merely the calculation amount required for going through N codebooks. Therefore, the complexity of the vector quantization could be decreased effectively.

7. 发明申请

WO2006089055A1 SPEECH ANALYZING SYSTEM WITH ADAPTIVE NOISE CODEBOOK 审中-公开
标题翻译：具有自适应噪声代码的语音分析系统
公开(公告)号：WO2006089055A1
公开(公告)日：2006-08-24
申请号：PCT/US2006/005523
申请日：2006-02-15
申请人： BBN TECHNOLOGIES CORP. , PREUSS, Robert David , FABRI, Darren Ross , CRUTHIRDS, Daniel Ramsay
发明人： PREUSS, Robert David , FABRI, Darren Ross , CRUTHIRDS, Daniel Ramsay
IPC分类号： G10L15/20 , G10L19/00
CPC分类号： G10L15/20 , G10L19/0018 , G10L19/12 , G10L19/20 , G10L21/0216 , G10L2019/0002 , G10L2019/0005
摘要： Presented herein are systems and methods for generating an adaptive noise codebook for use with electronic speech systems. The noise codebook includes a plurality of entries which may be updated based on environmental noise sounds. The speech system includes a speech codebook and the adaptive noise codebook. The system identifies speech sounds in an audio signal using the speech and noise codebooks.
摘要翻译：这里提出的是用于产生用于电子语音系统的自适应噪声码本的系统和方法。噪声码本包括可以基于环境噪声声音来更新的多个条目。语音系统包括语音码本和自适应噪声码本。该系统使用语音和噪声码本识别音频信号中的语音。

8. 发明申请

WO02043052A1 METHOD, DEVICE AND PROGRAM FOR CODING AND DECODING ACOUSTIC PARAMETER, AND METHOD, DEVICE AND PROGRAM FOR CODING AND DECODING SOUND 审中-公开
标题翻译：用于编码和解码声学参数的方法，装置和程序，以及用于编码和解码声音的方法，装置和程序
公开(公告)号：WO02043052A1
公开(公告)日：2002-05-30
申请号：PCT/JP2001/010332
申请日：2001-11-27
IPC分类号： G10L19/07 , G10L19/012 , G10L19/06 , G10L19/12 , G10L19/04 , G10L19/00
CPC分类号： G10L19/012 , G10L19/06 , G10L19/12 , G10L2019/0005 , G10L2019/0007
摘要： In coding and decoding an acoustic parameter, a weighted vector is generated by multiplying a code vector output in a past frame and a code vector selected in a present frame by weighting factors respectively selected from a factor code book and adding the products to each other.
摘要翻译：在对声学参数进行编码和解码时，通过将分别从因子码本中选择的加权因子和相加的乘积乘以在过去帧中输出的码矢量和当前帧中选择的码矢量来生成加权矢量。

9. 发明申请

WO00011657A1 COMPLETED FIXED CODEBOOK FOR SPEECH ENCODER 审中-公开
标题翻译：语音编码器的完整固定代码
公开(公告)号：WO00011657A1
公开(公告)日：2000-03-02
申请号：PCT/US1999/019591
申请日：1999-08-24
IPC分类号： G10L11/04 , G10L19/00 , G10L19/08 , G10L19/10 , G10L19/12 , G10L19/14 , G10L21/02
CPC分类号： G10L19/005 , G10L19/002 , G10L19/012 , G10L19/08 , G10L19/083 , G10L19/09 , G10L19/10 , G10L19/12 , G10L19/125 , G10L19/18 , G10L19/265 , G10L21/0364 , G10L2019/0005 , G10L2019/0007 , G10L2019/0011
摘要： A multi-rate speech codec supports a plurality of encoding bit rate modes by adaptively selecting encoding bit rate modes to match communication channel restrictions. In higher bit rate encoding modes, an accurate representation of speech through CELP (code excited linear prediction) and other associated modeling parameters are generated for higher quality decoding and reproduction. To achieve high quality in lower bit rate encoding modes, the speech encoder departs from the strict waveform matching criteria of regular CELP coders and strives to identify significant perceptual features of the input signal. To support lower bit rate encoding modes, a variety of techniques are applied many of which involve the classificaiton of the input signal. For each bit rate mode selected, pluralities of fixed or innovation subcodebooks are selected for use in generating innovation vectors.
摘要翻译：多速率语音编解码器通过自适应地选择编码比特率模式以匹配通信信道限制来支持多种编码比特率模式。在较高的比特率编码模式中，通过CELP（码激励线性预测）和其他相关联的建模参数的语音的精确表示被生成用于更高质量的解码和再现。为了在低比特率编码模式下实现高质量，语音编码器脱离了常规CELP编码器的严格波形匹配标准，并努力识别输入信号的重要感知特征。为了支持低比特率编码模式，应用了许多技术，其中许多技术涉及输入信号的分类。对于所选择的每个比特率模式，选择多个固定或创新子码本来用于产生创新向量。

10. 发明申请

WO2000011653A1 SPEECHENCODER USING CONTINUOUS WARPING COMBINED WITH LONG TERM PREDICTION 审中-公开
标题翻译：使用长时间预测组合连续加密的语音处理器
公开(公告)号：WO2000011653A1
公开(公告)日：2000-03-02
申请号：PCT/US1999019175
申请日：1999-08-24
申请人： CONEXANT SYSTEMS, INC.
发明人： CONEXANT SYSTEMS, INC. , GAO, Yang
IPC分类号： G10L19/08
CPC分类号： G10L19/005 , G10L19/002 , G10L19/012 , G10L19/08 , G10L19/083 , G10L19/09 , G10L19/10 , G10L19/12 , G10L19/125 , G10L19/18 , G10L19/265 , G10L21/0364 , G10L2019/0005 , G10L2019/0007 , G10L2019/0011
摘要： A multi-rate speech codec supports a plurality of encoding bit rate modes by adaptively selecting encoding bit rate modes to match communication channel restrictions. In higher bit rate encoding modes, an accurate representation of speech through CELP (code excited linear prediction) and other associated modeling parameters are generated for higher quality decoding and reproduction. To support lower bit rate encoding modes, a variety of techniques are applied many of which involve the classification of the input signal. The speech encoder continuously warps a weighted speech signal in long term preprocessing. The continuous warping is applied to a linear pitch lag contour that enables fast searching through linear time weighting. Optimal searching is performed within a limited range that is defined at least in part on sharpness and speech classification. The speech encoder generates the linear pitch lag contour from previous and current pitch lag values. Such continuous warping may also be applied in an open loop approach to the residual signal.
摘要翻译：多速率语音编解码器通过自适应地选择编码比特率模式以匹配通信信道限制来支持多种编码比特率模式。在较高的比特率编码模式中，通过CELP（码激励线性预测）和其他相关联的建模参数的语音的精确表示被生成用于更高质量的解码和再现。为了支持较低比特率编码模式，应用了许多技术，其中许多技术涉及输入信号的分类。语音编码器在长期预处理中连续扭曲加权语音信号。连续翘曲应用于能够通过线性时间加权进行快速搜索的线性音调滞后轮廓。在至少部分地基于锐度和语音分类的有限范围内执行最佳搜索。语音编码器从先前和当前音调滞后值产生线性音调滞后轮廓。这种连续翘曲也可以以开环方式应用于残余信号。

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