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

WO2020141108A1 METHOD, APPARATUS AND SYSTEM FOR HYBRID SPEECH SYNTHESIS 审中-公开
公开(公告)号：WO2020141108A1
公开(公告)日：2020-07-09
申请号：PCT/EP2019/086656
申请日：2019-12-20
申请人： DOLBY INTERNATIONAL AB
发明人： MUSTAFA, Ahmed , BISWAS, Arijit
IPC分类号： G10L19/08 , G06N3/02
摘要： A method of decoding an original speech signal for hybrid adversarial-parametric speech synthesis comprising:(a) receiving quantized original linear prediction coding parameters estimated by applying linear prediction coding analysis filtering to an original speech signal and a quantized compressed representation of a residual of the original speech signal; (b) dequantizing the original linear prediction coding parameters and the compressed representation of the residual; (c) inputting the dequantized compressed representation of the residual into a decoder part of a Generator for applying adversarial mapping from the compressed residual domain to a fake (first) signal domain; (d) outputting, by the decoder part of the Generator, a fake speech signal; (e) applying linear prediction coding analysis filtering to the fake speech signal for obtaining a corresponding fake residual; (f) reconstructing the original speech signal by applying linear prediction coding cross-synthesis filtering to the fake residual and the dequantized original linear prediction coding analysis parameters.

2. 发明申请

WO2012146757A1 EFFICIENT CONTENT CLASSIFICATION AND LOUDNESS ESTIMATION 审中-公开
标题翻译：有效内容分类和LOUDNESS估计
公开(公告)号：WO2012146757A1
公开(公告)日：2012-11-01
申请号：PCT/EP2012/057856
申请日：2012-04-27
申请人： DOLBY INTERNATIONAL AB , MUNDT, Harald , BISWAS, Arijit , MEISSNER, Rolf
发明人： MUNDT, Harald , BISWAS, Arijit , MEISSNER, Rolf
IPC分类号： G10L19/14
CPC分类号： G10L25/93 , G10L19/167 , G10L19/24 , G10L2025/783
摘要： Efficient Content Classification and Gated Loudness Estimation The present document relates to methods and systems for encoding an audio signal. The method comprises determining a spectral representation of the audio signal. The determining a spectral representation step may comprise determining modified discrete cosine transform, MDCT, coefficients, or a Quadrature Mirror Filter, QMF, filter bank representation of the audio signal. The method further comprises encoding the audio signal using the determined spectral representation; and classifying parts of the audio signal to be speech or non-speech based on the determined spectral representation. Finally, a loudness measure for the audio signal based on the speech parts is determined.
摘要翻译：高效内容分类和门控响度估计本文件涉及用于编码音频信号的方法和系统。该方法包括确定音频信号的频谱表示。确定频谱表示步骤可以包括确定音频信号的修正离散余弦变换，MDCT，系数或正交镜像滤波器QMF滤波器组表示。该方法还包括使用所确定的频谱表示对音频信号进行编码; 以及基于所确定的频谱表示将音频信号的部分分类为语音或非语音。最后，确定基于语音部分的音频信号的响度测量。

3. 发明申请

WO2012091938A1 RANKING REPRESENTATIVE SEGMENTS IN MEDIA DATA 审中-公开
标题翻译：在媒体数据中排名代表部分
公开(公告)号：WO2012091938A1
公开(公告)日：2012-07-05
申请号：PCT/US2011/065089
申请日：2011-12-15
申请人： DOLBY LABORATORIES LICENSING CORPORATION , DOLBY INTERNATIONAL AB , RESCH, Barbara , RADHAKRISHNAN, Regunathan , BISWAS, Arijit , ENGDEGARD, Jonas
发明人： RESCH, Barbara , RADHAKRISHNAN, Regunathan , BISWAS, Arijit , ENGDEGARD, Jonas
IPC分类号： G10H1/00 , G06K9/00 , G06F17/30
CPC分类号： H04R29/00 , G06F17/00 , G06F17/3053 , G10H1/0008 , G10H2210/061 , G10H2240/151 , G10L25/48
摘要： Techniques for ranking representative segments in media data are provided. Media features of many different types may be extracted from the media data. A plurality of ranking scores may be assigned to a plurality of candidate representative segments. Each individual candidate representative segment in the plurality of candidate representative segments comprises at least one scene in one or more statistical patterns in media features of the media data based on one or more types of features extractable from the media data. Each individual ranking score in the plurality of ranking scores may be assigned to an individual candidate representative segment in the plurality of candidate representative segments. A representative segment to be played to an end user may be selected from the candidate representative segments, based on the plurality of ranking scores.
摘要翻译：提供了在媒体数据中排列代表片段的技术。可以从媒体数据中提取许多不同类型的媒体特征。可以将多个排名得分分配给多个候选代表段。基于从媒体数据可提取的一种或多种类型的特征，多个候选代表段中的每个候选代表段包括媒体数据的媒体特征中的一个或多个统计模式中的至少一个场景。可以将多个排名得分中的每个个体排名得分分配给多个候选代表段中的个别候选代表段。可以基于多个排名得分从候选代表段中选择要向最终用户播放的代表段。

4. 发明申请

WO2021245015A1 METHOD AND APPARATUS FOR DETERMINING PARAMETERS OF A GENERATIVE NEURAL NETWORK 审中-公开
公开(公告)号：WO2021245015A1
公开(公告)日：2021-12-09
申请号：PCT/EP2021/064511
申请日：2021-05-31
申请人： DOLBY INTERNATIONAL AB
发明人： BISWAS, Arijit , PLAIN, Simon
IPC分类号： G10L19/26 , G10L25/30 , G10L21/0208 , G06N3/08 , G10L21/0364 , G06N3/0454 , G06N3/0472 , G06N3/082 , G06N3/084 , G06N3/088
摘要： Described herein is a method of determining parameters for a generative neural network for processing an audio signal, wherein the generative neural network includes an encoder stage mapping to a coded feature space and a decoder stage, each stage including a plurality of convolutional layers with one or more weight coefficients, the method comprising a plurality of cycles with sequential processes of: pruning the weight coefficients of either or both stages based on pruning control information, the pruning control information determining the number of weight coefficients that are pruned for respective convolutional layers; training the pruned generative neural network based on a set of training data; determining a loss for the trained and pruned generative neural network based on a loss function; and determining updated pruning control information based on the determined loss and a target loss. Further described are corresponding apparatus, programs, and computer-readable storage media.

5. 发明申请

WO2016091893A1 MDCT-DOMAIN ERROR CONCEALMENT 审中-公开
标题翻译： MDCT域错误隐藏
公开(公告)号：WO2016091893A1
公开(公告)日：2016-06-16
申请号：PCT/EP2015/079005
申请日：2015-12-08
申请人： DOLBY INTERNATIONAL AB
发明人： BISWAS, Arijit , FRIEDRICH, Tobias , PEICHL, Klaus
IPC分类号： G10L19/005 , G10L19/02
CPC分类号： G10L19/005 , G10L19/0212
摘要： An error-concealing audio decoding method comprises: receiving a packet comprising a set of MDCT coefficients encoding a frame of time-domain samples of an audio signal;identifying the received packet as erroneous;generating estimated MDCT coefficients to replace the set of MDCT coefficients of the erroneous packet, based on corresponding MDCT coefficients associated with a received packet directly preceding the erroneous packet;assigning signs of a first subset of MDCT coefficients of the estimated MDCT coefficients, wherein the first subset comprises such MDCT coefficients that are associated with tonal-like spectral bins, to coincide with signs of corresponding MDCT coefficients of said preceding packet;randomly assigning signs of a second subset of MDCT coefficients of the estimated MDCT coefficients, wherein the second subset comprises MDCT coefficients associated with noise-like spectral bins; replacing the erroneous packet by a concealment packet containing the estimated MDCT coefficients and the signs assigned.
摘要翻译：错误隐藏音频解码方法包括：接收包含编码音频信号的时域采样帧的MDCT系数集合的分组;识别接收到的分组是错误的;产生估计的MDCT系数以代替一组MDCT系数所述错误分组基于与直接在所述错误分组之前的接收分组相关联的相应MDCT系数;分配所述估计的MDCT系数的MDCT系数的第一子集的符号，其中所述第一子集包括与音调相关的这样的MDCT系数频谱箱，与所述前一分组的相应MDCT系数的符号一致;随机分配所估计的MDCT系数的MDCT系数的第二子集的符号，其中所述第二子集包括与噪声样频谱箱相关联的MDCT系数; 通过包含估计的MDCT系数和分配的符号的隐藏分组替换错误分组。

6. 发明申请

WO2014165543A1 COMPANDING APPARATUS AND METHOD TO REDUCE QUANTIZATION NOISE USING ADVANCED SPECTRAL EXTENSION 审中-公开
标题翻译：使用高级光谱扩展降低量化噪声的装置和方法
公开(公告)号：WO2014165543A1
公开(公告)日：2014-10-09
申请号：PCT/US2014/032578
申请日：2014-04-01
申请人： DOLBY LABORATORIES LICENSING CORPORATION , DOLBY INTERNATIONAL AB
发明人： HEDELIN, Per , BISWAS, Arijit , SCHUG, Michael , MELKOTE, Vinay
IPC分类号： G10L21/034 , H03G3/24 , G03G7/00 , H04B1/64
CPC分类号： G10L21/0232 , G10L19/008 , G10L19/0208 , G10L19/032 , G10L21/034 , G10L25/18 , G10L25/45 , H03G7/007 , H04B1/66
摘要： Embodiments are directed to a companding method and system for reducing coding noise in an audio codec. A compression process reduces an original dynamic range of an initial audio signal through a compression process that divides the initial audio signal into a plurality of segments using a defined window shape, calculates a wideband gain in the frequency domain using a non-energy based average of frequency domain samples of the initial audio signal, and applies individual gain values to amplify segments of relatively low intensity and attenuate segments of relatively high intensity. The compressed audio signal is then expanded back to substantially the original dynamic range that applies inverse gain values to amplify segments of relatively high intensity and attenuating segments of relatively low intensity. A QMF filterbank is used to analyze the initial audio signal to obtain a frequency domain representation.
摘要翻译：实施例涉及用于减少音频编解码器中的编码噪声的压扩方法和系统。压缩处理通过压缩处理来降低初始音频信号的原始动态范围，该压缩处理使用定义的窗口形状将初始音频信号分成多个段，使用基于非能量的平均值来计算频域中的宽带增益初始音频信号的频域样本，并且应用各个增益值来放大相对较低强度的片段并衰减相对较高强度的片段。压缩的音频信号然后被扩展回到基本上原始的动态范围，该动态范围应用反向增益值来放大相对较高强度的片段，并且衰减相对较低强度的段。使用QMF滤波器组来分析初始音频信号以获得频域表示。

7. 发明申请

WO2012091936A1 SCENE CHANGE DETECTION AROUND A SET OF SEED POINTS IN MEDIA DATA 审中-公开
标题翻译：在媒体数据中的一组种子点之间的场景变化检测
公开(公告)号：WO2012091936A1
公开(公告)日：2012-07-05
申请号：PCT/US2011/065086
申请日：2011-12-15
申请人： DOLBY LABORATORIES LICENSING CORPORATION , DOLBY INTERNATIONAL AB , RESCH, Barbara , RADHAKRISHNAN, Regunathan , BISWAS, Arijit , ENGDEGARD, Jonas
发明人： RESCH, Barbara , RADHAKRISHNAN, Regunathan , BISWAS, Arijit , ENGDEGARD, Jonas
IPC分类号： G10H1/00 , G06K9/00 , G06F17/30
CPC分类号： H04R29/00 , G06F17/00 , G06F17/3053 , G10H1/0008 , G10H2210/061 , G10H2240/151 , G10L25/48
摘要： Techniques for scene change detection around seed points in media data are provided. Media features of many different types may be extracted from the media data. One or more statistical patterns of media features in a plurality of time-wise intervals around a plurality of seed time points of the media data may be determined using one or more types of features extractable from the media data. At least one of the one or more types of features comprises a type of features that captures structural properties, tonality including harmony and melody, timbre, rhythm, loudness, stereo mix, or a quantity of sound sources as related to the media data. A plurality of beginning scene change points and a plurality of ending scene change points in the media data may be detected, based on the one or more statistical patterns, for the plurality of seed time points in the media data.
摘要翻译：提供媒体数据中种子点周围场景变化检测技术。可以从媒体数据中提取许多不同类型的媒体特征。可以使用从媒体数据可提取的一种或多种类型的特征来确定围绕媒体数据的多个种子时间点的多个时间间隔中的媒体特征的一个或多个统计模式。一种或多种类型的特征中的至少一种包括捕获与媒体数据相关的结构性质，包括和声和旋律的音调，音色，节奏，响度，立体声混合或数量的声源的特征的类型。可以基于媒体数据中的多个种子时间点的一个或多个统计模式来检测媒体数据中的多个起始场景变化点和多个结束场景变化点。

8. 发明申请

WO2020187587A1 METHOD AND APPARATUS FOR UPDATING A NEURAL NETWORK 审中-公开
公开(公告)号：WO2020187587A1
公开(公告)日：2020-09-24
申请号：PCT/EP2020/055869
申请日：2020-03-05
申请人： DOLBY INTERNATIONAL AB
发明人： FERSCH, Christof , BISWAS, Arijit
IPC分类号： G06N3/04 , G06N3/08
摘要： Described herein is a method of generating a media bitstream to transmit parameters for updating a neural network implemented in a decoder, wherein the method includes the steps of: (a) determining at least one set of parameters for updating the neural network; (b) encoding the at least one set of parameters and media data to generate the media bitstream; and (c) transmitting the media bitstream to the decoder for updating the neural network with the at least one set of parameters. Described herein are further a method for updating a neural network implemented in a decoder, an apparatus for generating a media bitstream to transmit parameters for updating a neural network implemented in a decoder, an apparatus for updating a neural network implemented in a decoder and computer program products comprising a computer-readable storage medium with instructions adapted to cause the device to carry out said methods when executed by a device having processing capability.

9. 发明申请

WO2020039000A1 CODING DENSE TRANSIENT EVENTS WITH COMPANDING 审中-公开
公开(公告)号：WO2020039000A1
公开(公告)日：2020-02-27
申请号：PCT/EP2019/072377
申请日：2019-08-21
申请人： DOLBY INTERNATIONAL AB
发明人： BISWAS, Arijit , MUNDT, Harald
IPC分类号： G10L21/034 , H04B1/64
摘要： Embodiments are directed to a companding method and system for reducing coding noise in an audio codec. A method of processing an audio signal includes the following operations. A system receives an audio signal. The system determines that a first frame of the audio signal includes a sparse transient signal. The system determines that a second frame of the audio signal includes a dense transient signal. The system compresses/expands (compands) the audio signal using a companding rule that applies a first companding exponent to the first frame of the audio signal and applies a second companding exponent to the second frame of the audio signal, each companding exponent being used to derive a respective degree of dynamic range compression and expansion for a corresponding frame. The system then provides the companded audio signal to a downstream device.

10. 发明申请

WO2016180704A1 DIALOG ENHANCEMENT COMPLEMENTED WITH FREQUENCY TRANSPOSITION 审中-公开
标题翻译：通过频率交换完成对话增强
公开(公告)号：WO2016180704A1
公开(公告)日：2016-11-17
申请号：PCT/EP2016/060004
申请日：2016-05-04
申请人： DOLBY INTERNATIONAL AB
发明人： BISWAS, Arijit
IPC分类号： H04R25/00
CPC分类号： H04R25/353 , H04R25/505 , H04R2225/43
摘要： A method, a system and a computer program product are disclosed for enhancing an audio signal in relation to a hearing impairment. An input signal is obtained comprising input sub-band signals in a frequency range comprising a source range and a target range. The input sub-band signals in the source range are selectively transposed into transposed sub-band signals in the target range according to a predefined transposing rule. A masking threshold is determined based on a predefined perceptual model and perceptually relevant sub-band signals of the transposed sub-band signals in the target range exceeding the masking threshold are detected. Input sub-band signals in the target range are selectively replaced with corresponding detected perceptually relevant sub-band signals of the transposed sub-band signals in the target range.
摘要翻译：公开了用于增强与听力障碍有关的音频信号的方法，系统和计算机程序产品。获得包括在源范围和目标范围的频率范围内的输入子带信号的输入信号。源范围中的输入子带信号根据预定的转置规则被选择性地转置在目标范围内的转置子带信号中。基于预定知觉模型确定屏蔽阈值，并且检测超过掩蔽阈值的目标范围内的转置子带信号的感知相关子带信号。在目标范围内的输入子带信号被选择性地替换为目标范围中转置的子带信号的相应检测到的感知相关子带信号。

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