Memory bank signal coupling buffer and method
    1.
    发明授权
    Memory bank signal coupling buffer and method 有权
    存储体信号耦合缓冲器和方法

    公开(公告)号:US08400809B2

    公开(公告)日:2013-03-19

    申请号:US13071303

    申请日:2011-03-24

    IPC分类号: G11C5/06

    摘要: A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.

    摘要翻译: 存储器阵列包含通过多个数据线彼此耦合的多个存储体。 每个数据线被分成阵列内的多个段。 相应的双向缓冲器将读数据从第一方向上的一个段耦合到另一个段,并且将数据从一个段耦合到与第一方向相反的第二方向的另一方。 数据线可以是将不同存储单元组彼此耦合的本地数据读/写线和相应的数据端,将相应列中的存储单元耦合到相应的读出放大器的数字线,激活存储单元中的存储单元的字线 相应的行或阵列内的其他一些信号线。 存储器阵列还包括用于将各个数据线的段预充电为预充电电压的预充电电路。

    Adaptive Pairwise Preferences in Recommenders
    2.
    发明申请
    Adaptive Pairwise Preferences in Recommenders 有权
    推荐者中的自适应成对偏好

    公开(公告)号:US20120143802A1

    公开(公告)日:2012-06-07

    申请号:US12958434

    申请日:2010-12-02

    IPC分类号: G06F15/18 G06N5/02

    摘要: Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.

    摘要翻译: 方法,系统和产品适应具有成对反馈的推荐系统。 一个成对的问题是向用户提出的。 收到一个响应,选择对成对问题中的一对项目的偏好。 潜在因素模型适用于纳入响应,并且基于响应向用户推荐项目。

    System and method for feature-rich continuous space language models
    3.
    发明授权
    System and method for feature-rich continuous space language models 有权
    功能丰富的连续空间语言模型的系统和方法

    公开(公告)号:US09092425B2

    公开(公告)日:2015-07-28

    申请号:US12963161

    申请日:2010-12-08

    IPC分类号: G06F17/27 G06F17/28

    CPC分类号: G06F17/28

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.

    摘要翻译: 这里公开了用于预测语言模型的单词概率的系统,方法和非暂时的计算机可读存储介质。 配置为实施该方法的示例性系统接收与该单词序列相关联的单词序列和外部数据序列,并将该单词序列映射到对应于词汇大小的X维向量。 然后系统根据外部数据对每个X维向量进行处理,以产生各自的Y维向量,其中每个Y维向量表示密集的连续空间,并且输出至少一个预测的下一个单词以跟随单词序列 基于相应的Y维向量。 作为二进制稀疏表示的X维向量可以比作为密集连续空间的Y维向量更高的维度。 外部数据可以包括在给定历史中的部分词汇标签,主题信息,单词相似性,单词关系,特定主题以及后续部分语音。

    MEMORY BANK SIGNAL COUPLING BUFFER AND METHOD
    4.
    发明申请
    MEMORY BANK SIGNAL COUPLING BUFFER AND METHOD 有权
    存储器银行信号耦合缓冲器和方法

    公开(公告)号:US20100177571A1

    公开(公告)日:2010-07-15

    申请号:US12353661

    申请日:2009-01-14

    IPC分类号: G11C7/00 G11C8/00 H03L5/00

    摘要: A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.

    摘要翻译: 存储器阵列包含通过多条数据线彼此耦合的多个存储体。 每个数据线被分成阵列内的多个段。 相应的双向缓冲器将读数据从第一方向上的一个段耦合到另一个段,并且将数据从一个段耦合到与第一方向相反的第二方向的另一方。 数据线可以是将不同存储单元组彼此耦合的本地数据读/写线和相应的数据端,将相应列中的存储单元耦合到相应的读出放大器的数字线,激活存储单元中的存储单元的字线 相应的行或阵列内的其他一些信号线。 存储器阵列还包括用于将各个数据线的段预充电为预充电电压的预充电电路。

    SYSTEM AND METHOD FOR COMBINING FRAME AND SEGMENT LEVEL PROCESSING, VIA TEMPORAL POOLING, FOR PHONETIC CLASSIFICATION
    5.
    发明申请
    SYSTEM AND METHOD FOR COMBINING FRAME AND SEGMENT LEVEL PROCESSING, VIA TEMPORAL POOLING, FOR PHONETIC CLASSIFICATION 有权
    用于组合框架和分段水平处理的系统和方法,通过时间池,用于电话分类

    公开(公告)号:US20130103402A1

    公开(公告)日:2013-04-25

    申请号:US13281102

    申请日:2011-10-25

    IPC分类号: G10L15/04 G10L15/00

    CPC分类号: G10L15/02 G10L15/08 G10L15/16

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations. Based on the scores, the plurality of segmental classification units selects a class label and returns a result.

    摘要翻译: 本文公开了用于通过时间池来组合帧和段级处理用于语音分类的系统,方法和非暂时的计算机可读存储介质。 帧处理器单元接收输入并从输入中提取与时间相关的特征。 多个池化接口单元基于集合时间依赖特征并根据多个选择策略选择多个时间相关特征来生成多个特征向量。 接下来,多个分段分类单元生成特征向量的得分。 每个分段分类单元(SCU)可专用于特定的汇聚接口单元(PIU)以形成PIU-SCU组合。 可以进一步组合多个PIU-SCU组合以形成组合的集合,并且可以通过改变PIU-SCU组合使用的合并操作来使集合多样化。 基于分数,多个分段分类单元选择分类标签并返回结果。

    SYSTEM AND METHOD FOR LEARNING LATENT REPRESENTATIONS FOR NATURAL LANGUAGE TASKS
    6.
    发明申请
    SYSTEM AND METHOD FOR LEARNING LATENT REPRESENTATIONS FOR NATURAL LANGUAGE TASKS 有权
    用于学习自然语言任务的专有代表的系统和方法

    公开(公告)号:US20120150531A1

    公开(公告)日:2012-06-14

    申请号:US12963126

    申请日:2010-12-08

    IPC分类号: G06F17/27

    CPC分类号: G06F17/28

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for learning latent representations for natural language tasks. A system configured to practice the method analyzes, for a first natural language processing task, a first natural language corpus to generate a latent representation for words in the first corpus. Then the system analyzes, for a second natural language processing task, a second natural language corpus having a target word, and predicts a label for the target word based on the latent representation. In one variation, the target word is one or more word such as a rare word and/or a word not encountered in the first natural language corpus. The system can optionally assigning the label to the target word. The system can operate according to a connectionist model that includes a learnable linear mapping that maps each word in the first corpus to a low dimensional latent space.

    摘要翻译: 本文公开了用于学习自然语言任务的潜在表示的系统,方法和非暂时的计算机可读存储介质。 一种被配置为练习该方法的系统,分析第一自然语言处理任务中的第一自然语言语料库以产生第一语料库中的单词的潜在表示。 然后,系统针对第二自然语言处理任务分析具有目标词的第二自然语言语料库,并且基于潜在表示来预测目标词的标签。 在一个变体中,目标词是一个或多个单词,例如在第一自然语言语料库中不遇到的罕见单词和/或单词。 系统可以选择将标签分配给目标字。 该系统可以根据连接主义模型来操作,该连接主义模型包括将第一语料库中的每个单词映射到低维空间的可学习的线性映射。

    System and method for dynamic facial features for speaker recognition
    7.
    发明授权
    System and method for dynamic facial features for speaker recognition 有权
    用于说话者识别的动态面部特征的系统和方法

    公开(公告)号:US08897500B2

    公开(公告)日:2014-11-25

    申请号:US13101704

    申请日:2011-05-05

    IPC分类号: G06K9/00 G10L17/24 G06F21/32

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

    摘要翻译: 本文公开了用于执行说话者验证的系统,方法和非暂时的计算机可读存储介质。 被配置为实施该方法的系统接收到验证说话者的请求,产生对该请求是唯一的文本挑战,并且响应该请求提示说话者发出文本挑战。 然后当扬声器发出文本挑战时,系统记录扬声器的动态图像特征,并且基于动态图像特征和文本挑战来执行说话者验证。 录制扬声器的动态图像功能可以包括在说出文本挑战时录制扬声器的视频。 动态特征可以包括扬声器的头部,嘴唇,嘴巴,眼睛和/或眉毛的运动模式。 动态图像特征可以涉及讲话者讲话的语音内容,语音韵律以及响应于挑战内容的说话者的面部表情。

    System and method for combining frame and segment level processing, via temporal pooling, for phonetic classification
    8.
    发明授权
    System and method for combining frame and segment level processing, via temporal pooling, for phonetic classification 有权
    用于组合帧和段级处理的系统和方法,通过时间池进行语音分类

    公开(公告)号:US08886533B2

    公开(公告)日:2014-11-11

    申请号:US13281102

    申请日:2011-10-25

    IPC分类号: G10L15/08 G10L15/16 G10L15/02

    CPC分类号: G10L15/02 G10L15/08 G10L15/16

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations. Based on the scores, the plurality of segmental classification units selects a class label and returns a result.

    摘要翻译: 本文公开了用于通过时间池来组合帧和段级处理用于语音分类的系统,方法和非暂时的计算机可读存储介质。 帧处理器单元接收输入并从输入中提取与时间相关的特征。 多个池化接口单元基于集合时间相关特征并根据多个选择策略选择多个时间相关特征来生成多个特征向量。 接下来,多个分段分类单元生成特征向量的得分。 每个分段分类单元(SCU)可专用于特定的汇聚接口单元(PIU)以形成PIU-SCU组合。 可以进一步组合多个PIU-SCU组合以形成组合的集合,并且可以通过改变PIU-SCU组合使用的合并操作来使集合多样化。 基于分数,多个分段分类单元选择分类标签并返回结果。

    Adaptive pairwise preferences in recommenders
    9.
    发明授权
    Adaptive pairwise preferences in recommenders 有权
    推荐者的自适应成对偏好

    公开(公告)号:US08589319B2

    公开(公告)日:2013-11-19

    申请号:US12958434

    申请日:2010-12-02

    IPC分类号: G06F15/18

    摘要: Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.

    摘要翻译: 方法,系统和产品适应具有成对反馈的推荐系统。 一个成对的问题是向用户提出的。 收到一个响应,选择对成对问题中的一对项目的偏好。 潜在因素模型适用于纳入响应,并且基于响应向用户推荐项目。

    SYSTEM AND METHOD FOR DYNAMIC FACIAL FEATURES FOR SPEAKER RECOGNITION
    10.
    发明申请
    SYSTEM AND METHOD FOR DYNAMIC FACIAL FEATURES FOR SPEAKER RECOGNITION 有权
    用于声音识别的动态特征的系统和方法

    公开(公告)号:US20120281885A1

    公开(公告)日:2012-11-08

    申请号:US13101704

    申请日:2011-05-05

    IPC分类号: G06K9/00

    摘要: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

    摘要翻译: 本文公开了用于执行说话者验证的系统,方法和非暂时的计算机可读存储介质。 被配置为实施该方法的系统接收到验证说话者的请求,产生对该请求是唯一的文本挑战,并且响应该请求提示说话者发出文本挑战。 然后当扬声器发出文本挑战时,系统记录扬声器的动态图像特征,并且基于动态图像特征和文本挑战来执行说话者验证。 录制扬声器的动态图像功能可以包括在说出文本挑战时录制扬声器的视频。 动态特征可以包括扬声器的头部,嘴唇,嘴巴,眼睛和/或眉毛的运动模式。 动态图像特征可以涉及讲话者讲话的语音内容,语音韵律以及响应于挑战内容的说话者的面部表情。