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

WO2018048934A1 GENERATING AUDIO USING NEURAL NETWORKS 审中-公开
标题翻译：用神经网络产生音频
公开(公告)号：WO2018048934A1
公开(公告)日：2018-03-15
申请号：PCT/US2017/050320
申请日：2017-09-06
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： VAN DEN OORD, Aaron Gerard Antonius , DIELEMAN, Sander Etienne Lea , KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , VINYALS, Oriol
IPC分类号： G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.
摘要翻译：包括在计算机存储介质上编码的计算机程序的方法，系统和装置，用于生成音频数据的输出序列，该音频数据的输出序列在多个时间步骤中的每个时间步骤包括相应的音频样本。对于每个时间步骤，这些方法之一包括：提供音频数据的当前序列作为卷积子网络的输入，其中当前序列包括在输出序列中的时间步长之前的每个时间步骤处的相应音频样本，且其中所述卷积子网络经配置以处理所述当前音频数据序列以产生所述时间步骤的替代表示; 以及将所述时间步长的所述替代表示作为输入提供给输出层，其中所述输出层被配置为：处理所述替代表示以产生定义所述时间步骤的多个可能音频样本上的得分分布的输出。 / p>

2. 发明申请

WO2021156511A1 RECURRENT UNIT FOR GENERATING OR PROCESSING A SEQUENCE OF IMAGES 审中-公开
公开(公告)号：WO2021156511A1
公开(公告)日：2021-08-12
申请号：PCT/EP2021/052980
申请日：2021-02-08
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： LUC, Pauline , CLARK, Aidan , DIELEMAN, Sander Etienne Lea , SIMONYAN, Karen
IPC分类号： G06N3/04 , G06N3/08 , G06T11/00 , G06T3/40 , G06T7/10
摘要： A recurrent unit is proposed which, at each of a series of time steps receives a corresponding input vector and generates an output at the time step having at least one component for each of a two-dimensional array of pixels. The recurrent unit is configured, at each of the series of time steps except the first, to receive the output of the recurrent unit at the preceding time step, and to apply to the output of the recurrent unit at the preceding time step at least one convolution which depends on the input vector at the time step. The convolution further depends upon the output of the recurrent unit at the preceding time step. This convolution generates a warped dataset which has at least one component for each pixel of the array. The output of the recurrent unit at each time step is based on the warped dataset and the input vector.

3. 发明申请

WO2022189493A2 GENERATING OUTPUT SIGNALS USING VARIABLE-RATE DISCRETE REPRESENTATIONS 审中-公开
公开(公告)号：WO2022189493A2
公开(公告)日：2022-09-15
申请号：PCT/EP2022/056014
申请日：2022-03-09
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： DIELEMAN, Sander Etienne Lea
IPC分类号： G10L19/16 , G10L25/30
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output signals using variable-rate discrete representations. One of the methods includes generating, using a generative neural network, an event sequence representing a run-length encoding of a discrete representation of the audio signal, the event sequence comprising a respective event at each of a plurality of event sequence time steps; generating the discrete representation of the audio signal from the event sequence using run-length decoding; and processing the discrete representation using a decoder neural network, wherein the decoder neural network is configured to process the discrete representation of the audio signal to generate the prediction of the audio signal.

4. 发明申请

WO2021245292A1 GENERATING AUDIO DATA USING UNALIGNED TEXT INPUTS WITH AN ADVERSARIAL NETWORK 审中-公开
公开(公告)号：WO2021245292A1
公开(公告)日：2021-12-09
申请号：PCT/EP2021/065195
申请日：2021-06-07
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： DONAHUE, Jeffrey , SIMONYAN, Karen , DIELEMAN, Sander Etienne Lea , BINKOWSKI, Mikolaj , ELSEN, Erich Konrad
IPC分类号： G06N3/04 , G06N3/08 , G10L13/00 , G06N3/0454 , G06N3/0481 , G06N3/088 , G10L13/02 , G10L13/047 , G10L2013/105 , G10L25/30
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a generative neural network to convert conditioning text inputs to audio outputs. The generative neural network includes an alignment neural network that is configured to receive a generative input that includes the conditioning text input and to process the generative input to generate an aligned conditioning sequence that comprises a respective feature representation at each of a plurality of first time steps and that is temporally aligned with the audio output.

5. 发明申请

WO2021058746A1 HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS 审中-公开
公开(公告)号：WO2021058746A1
公开(公告)日：2021-04-01
申请号：PCT/EP2020/076908
申请日：2020-09-25
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： BINKOWSKI, Mikolaj , SIMONYAN, Karen , DONAHUE, Jeffrey , CLARK, Aidan , DIELEMAN, Sander Etienne Lea , ELSEN, Erich Konrad , RUS, Luis Carlos Cobo , CASAGRANDE, Norman
IPC分类号： G06N3/04 , G06N3/08 , G10L13/02 , G10L13/047 , G10L25/30 , G10L25/45
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output audio examples using a generative neural network. One of the methods includes obtaining a training conditioning text input; processing a training generative input comprising the training conditioning text input using a feedforward generative neural network to generate a training audio output; processing the training audio output using each of a plurality of discriminators, wherein the plurality of discriminators comprises one or more conditional discriminators and one or more unconditional discriminators; determining a first combined prediction by combining the respective predictions of the plurality of discriminators; and determining an update to current values of a plurality of generative parameters of the feedforward generative neural network to increase a first error in the first combined prediction.

6. 发明申请

WO2018048945A1 PROCESSING SEQUENCES USING CONVOLUTIONAL NEURAL NETWORKS 审中-公开
标题翻译：用卷积神经网络处理序列
公开(公告)号：WO2018048945A1
公开(公告)日：2018-03-15
申请号：PCT/US2017/050335
申请日：2017-09-06
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： VAN DEN OORD, Aaron Gerard Antonius , DIELEMAN, Sander Etienne Lea , KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , VINYALS, Oriol , ESPEHOLT, Lasse
IPC分类号： G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating of generating a neural network output from an input sequence. One of the methods includes, for each of the inputs, providing a current input sequence that comprises the input and the inputs preceding the input in the input sequence to a convolutional subnetwork comprising a plurality of dilated convolutional neural network layers, wherein the convolutional subnetwork is configured to, for each of the plurality of inputs: receive the current input sequence for the input, and process the current input sequence to generate an alternative representation for the input; and providing the alternative representations to an output subnetwork, wherein the output subnetwork is configured to receive the alternative representations and to process the alternative representations to generate the neural network output.
摘要翻译：包括在计算机存储介质上编码的计算机程序的方法，系统和装置，用于从输入序列产生神经网络输出。其中一种方法包括对于每个输入提供当前输入序列，该输入序列包括输入和输入之前的输入之前的输入到包括多个膨胀卷积神经网络层的卷积子网络，其中卷积子网络是被配置为针对所述多个输入中的每一个：接收所述输入的当前输入序列，并且处理所述当前输入序列以生成所述输入的替代表示; 以及将所述替代表示提供给输出子网络，其中所述输出子网络被配置为接收所述替代表示并处理所述替代表示以生成所述神经网络输出。

7. 发明公开

EP3497629A1 GENERATING AUDIO USING NEURAL NETWORKS 审中-公开
公开(公告)号：EP3497629A1
公开(公告)日：2019-06-19
申请号：EP17780543.9
申请日：2017-09-06
申请人： Deepmind Technologies Limited
发明人： VAN DEN OORD, Aaron Gerard Antonius , DIELEMAN, Sander Etienne Lea , KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , VINYALS, Oriol
IPC分类号： G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.

8. 发明公开

EP3822863A1 GENERATING AUDIO USING NEURAL NETWORKS 审中-公开
公开(公告)号：EP3822863A1
公开(公告)日：2021-05-19
申请号：EP20195353.6
申请日：2017-09-06
申请人： DeepMind Technologies Limited
发明人： VAN DEN OORD, Aaron Gerard Antonius , DIELEMAN, Sander Etienne Lea , KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , VINYALS, Oriol
IPC分类号： G06N3/04
摘要： A method of training a neural network system to generate an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes processing a training sequence of audio data using a convolutional subnetwork. The convolutional subnetwork is configured to, for each of the time steps, receive a current sequence of audio data that comprises an audio sample at each time step that precedes the time step in the training sequence, and process the current sequence of audio data to generate an alternative representation for the time step. The alternative representation for the time step is used to generate an output that defines a score distribution over a plurality of possible audio samples for the time step. The neural network system is trained using supervised learning based on the input audio samples and the output score distribution.

9. 发明公开

EP4305619A2 GENERATING OUTPUT SIGNALS USING VARIABLE-RATE DISCRETE REPRESENTATIONS 审中-公开
公开(公告)号：EP4305619A2
公开(公告)日：2024-01-17
申请号：EP22714373.2
申请日：2022-03-09
申请人： DeepMind Technologies Limited
发明人： DIELEMAN, Sander Etienne Lea
IPC分类号： G10L19/16 , G10L25/30

10. 发明公开

EP4018383A1 HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS 审中-公开
公开(公告)号：EP4018383A1
公开(公告)日：2022-06-29
申请号：EP20781342.9
申请日：2020-09-25
申请人： DeepMind Technologies Limited
发明人： BINKOWSKI, Mikolaj , SIMONYAN, Karen , DONAHUE, Jeffrey , CLARK, Aidan , DIELEMAN, Sander Etienne Lea , ELSEN, Erich Konrad , RUS, Luis Carlos Cobo , CASAGRANDE, Norman
IPC分类号： G06N3/04 , G06N3/08 , G10L13/02 , G10L13/047 , G10L25/30 , G10L25/45

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