-
公开(公告)号：US09858524B2
公开(公告)日：2018-01-02
申请号：US14941454
申请日：2015-11-13
Applicant: Google Inc.
Inventor： Samy Bengio , Oriol Vinyals , Alexander Toshkov Toshev , Dumitru Erhan
CPC classification number: G06N3/0472 , G06F17/28 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.
-
公开(公告)号：US20160180215A1
公开(公告)日：2016-06-23
申请号：US14976121
申请日：2015-12-21
Applicant: Google Inc.
Inventor： Oriol Vinyals , Lukasz Mieczyslaw Kaiser
CPC classification number: G06F17/2705 , G06N3/0445 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating parse trees for input text segments. One of the methods includes obtaining an input text segment, processing the input text segment using a first long short term memory (LSTM) neural network to convert the input text segment into an alternative representation for the input text segment, and processing the alternative representation for the input text segment using a second LSTM neural network to generate a linearized representation of a parse tree for the input text segment.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于为输入文本段生成解析树。 其中一种方法包括获取输入文本段，使用第一长短期存储器（LSTM）神经网络处理输入文本段，以将输入文本段转换为输入文本段的备选表示，并处理替代表示 所述输入文本段使用第二LSTM神经网络来生成所述输入文本段的解析树的线性化表示。
-
公开(公告)号：US20170200076A1
公开(公告)日：2017-07-13
申请号：US15406557
申请日：2017-01-13
Applicant: Google Inc.
Inventor： Oriol Vinyals , Samuel Bengio
CPC classification number: G06N3/0445 , G06N3/0454
Abstract: In one aspect, this specification describes a recurrent neural network system implemented by one or more computers that is configured to process input sets to generate neural network outputs for each input set. The input set can be a collection of multiple inputs for which the recurrent neural network should generate the same neural network output regardless of the order in which the inputs are arranged in the collection. The recurrent neural network system can include a read neural network, a process neural network, and a write neural network. In another aspect, this specification describes a system implemented as computer programs on one or more computers in one or more locations that is configured to train a recurrent neural network that receives a neural network input and sequentially emits outputs to generate an output sequence for the neural network input.
-
公开(公告)号：US20170140753A1
公开(公告)日：2017-05-18
申请号：US15349245
申请日：2016-11-11
Applicant: Google Inc.
Inventor： Navdeep Jaitly , Quoc V. Le , Oriol Vinyals , Samuel Bengio , Ilya Sutskever
CPC classification number: G10L15/16 , G05B13/027 , G06F17/276 , G06F17/289 , G06N3/0445 , G10L15/02 , G10L15/26 , G10L2015/025
Abstract: A system can be configured to perform tasks such as converting recorded speech to a sequence of phonemes that represent the speech, converting an input sequence of graphemes into a target sequence of phonemes, translating an input sequence of words in one language into a corresponding sequence of words in another language, or predicting a target sequence of words that follow an input sequence of words in a language (e.g., a language model). In a speech recognizer, the RNN system may be used to convert speech to a target sequence of phonemes in real-time so that a transcription of the speech can be generated and presented to a user, even before the user has completed uttering the entire speech input.
-
公开(公告)号：US09378733B1
公开(公告)日：2016-06-28
申请号：US13860982
申请日：2013-04-11
Applicant: Google Inc.
Inventor： Vincent O. Vanhoucke , Oriol Vinyals , Patrick An Phu Nguyen , Maria Carolina Parada San Martin , Johan Schalkwyk
CPC classification number: G10L15/08 , G10L15/02 , G10L2015/088
Abstract: Embodiments pertain to automatic speech recognition in mobile devices to establish the presence of a keyword. An audio waveform is received at a mobile device. Front-end feature extraction is performed on the audio waveform, followed by acoustic modeling, high level feature extraction, and output classification to detect the keyword. Acoustic modeling may use a neural network or a vector quantization dictionary and high level feature extraction may use pooling.
Abstract translation: 实施例涉及移动设备中的自动语音识别以建立关键字的存在。 在移动设备处接收音频波形。 对音频波形执行前端特征提取，然后进行声学建模，高级特征提取和输出分类，以检测关键字。 声学建模可以使用神经网络或矢量量化字典，并且高级特征提取可以使用池。
-
Patent Agency Ranking
公开(公告)号：US20160140435A1
公开(公告)日：2016-05-19
申请号：US14941454
申请日：2015-11-13
Applicant: Google Inc.
Inventor： Samy Bengio , Oriol Vinyals , Alexander Toshkov Toshev , Dumitru Erhan
CPC classification number: G06N3/0472 , G06F17/28 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于产生输入图像的描述。 方法之一包括获取输入图像; 使用第一神经网络处理所述输入图像以生成所述输入图像的替代表示; 以及使用第二神经网络处理所述输入图像的替代表示，以生成描述所述输入图像的目标自然语言中的多个单词的序列。
-
公开(公告)号：US20170192956A1
公开(公告)日：2017-07-06
申请号：US15396091
申请日：2016-12-30
Applicant: Google Inc.
Inventor： Lukasz Mieczyslaw Kaiser , Oriol Vinyals
CPC classification number: G06F17/271 , G06N3/0445
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating parse trees for input text segments. One of the methods includes obtaining an input text segment comprising a plurality of inputs arranged according to an input order; processing the inputs in the input text segment using an encoder long short term memory (LSTM) neural network to generate a respective encoder hidden state for each input in the input text segment; and processing the respective encoder hidden states for the inputs in the input text segment using an attention-based decoder LSTM neural network to generate a linearized representation of a parse tree for the input text segment.
-
公开(公告)号：US20160117316A1
公开(公告)日：2016-04-28
申请号：US14921925
申请日：2015-10-23
Applicant: Google Inc.
Inventor： Quoc V. Le , Minh-Thang Luong , Ilya Sutskever , Oriol Vinyals , Wojciech Zaremba
CPC classification number: G06F17/2881 , G06F7/023 , G06F7/10 , G06F17/2735 , G06F17/2818 , G06F17/2827 , G06N3/0445 , G06N3/0454 , G10L15/02 , G10L15/16
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.
Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于具有罕见文字处理的神经翻译系统。 其中一种方法是训练神经网络翻译系统，以分别在源语言和目标语言中跟踪目标语句中的未知单词的源语句中的源，并且包括从并行语料库导出对齐数据，对齐数据 在平行语料库中的每对源和目标语言句子中识别对齐的源词和目标词; 根据对齐数据和平行语料库中的句子注释罕见词模型，以生成配对的源语言和目标语言句子的训练数据集; 并在训练数据集上训练神经网络翻译模型。
-
公开(公告)号：US09990918B1
公开(公告)日：2018-06-05
申请号：US15788300
申请日：2017-10-19
Applicant: Google Inc.
Inventor： William Chan , Navdeep Jaitly , Quoc V. Le , Oriol Vinyals , Noam M. Shazeer
IPC: G10L15/16 , G06F17/22 , G10L15/183 , G10L15/26
CPC classification number: G10L15/16
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.
-
公开(公告)号：US09799327B1
公开(公告)日：2017-10-24
申请号：US15055476
申请日：2016-02-26
Applicant: Google Inc.
Inventor： William Chan , Navdeep Jaitly , Quoc V. Le , Oriol Vinyals , Noam M. Shazeer
IPC: G10L15/16 , G10L15/26 , G06F17/22 , G10L15/183
CPC classification number: G10L15/16
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.027 seconds)
