公开(公告)号：US09558738B2

公开(公告)日：2017-01-31

申请号：US13042671

申请日：2011-03-08

申请人： Enrico Bocchieri ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

发明人： Enrico Bocchieri ,  Diamantino Antonio Caseiro ,  Dimitrios Dimitriadis

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/14

CPC分类号： G10L15/063 ,  G10L15/14

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating an acoustic model for use in speech recognition. A system configured to practice the method first receives training data and identifies non-contextual lexical-level features in the training data. Then the system infers sentence-level features from the training data and generates a set of decision trees by node-splitting based on the non-contextual lexical-level features and the sentence-level features. The system decorrelates training vectors, based on the training data, for each decision tree in the set of decision trees to approximate full-covariance Gaussian models, and then can train an acoustic model for use in speech recognition based on the training data, the set of decision trees, and the training vectors.

摘要翻译： 本文公开了用于生成用于语音识别的声学模型的系统，方法和非暂时的计算机可读存储介质。 被配置为练习该方法的系统首先接收训练数据并识别训练数据中的非上下文词汇级特征。 然后，该系统从训练数据推导出句子级特征，并基于非上下文词汇级特征和句子级特征，通过节点分割生成一组决策树。 该系统基于训练数据对训练数据进行解相关，对于决策树组中的每个决策树，以近似全协方差高斯模型，然后可以基于训练数据训练用于语音识别的声学模型，该集合 的决策树，以及训练矢量。

公开(公告)号：US20110144973A1

公开(公告)日：2011-06-16

申请号：US12638667

申请日：2009-12-15

申请人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

发明人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

IPC分类号： G06F17/28 ,  G10L15/06 ,  G10L15/04

CPC分类号： G10L15/08 ,  G06F17/289 ,  G10L15/19 ,  G10L15/197 ,  G10L25/54 ,  G10L2015/081 ,  G10L2015/228

摘要： Disclosed herein are systems, methods, and computer-readable storage media for a speech recognition application for directory assistance that is based on a user's spoken search query. The spoken search query is received by a portable device and portable device then determines its present location. Upon determining the location of the portable device, that information is incorporated into a local language model that is used to process the search query. Finally, the portable device outputs the results of the search query based on the local language model.

摘要翻译： 本文公开了用于基于用户的口语搜索查询的目录帮助的语音识别应用的系统，方法和计算机可读存储介质。 口头搜索查询由便携式设备接收，便携式设备随后确定其当前位置。 在确定便携式设备的位置时，该信息被并入用于处理搜索查询的本地语言模型中。 最后，便携式设备基于本地语言模型输出搜索查询的结果。

公开(公告)号：US08892443B2

公开(公告)日：2014-11-18

申请号：US12638667

申请日：2009-12-15

申请人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

发明人： Enrico Bocchieri ,  Diamantino Antonio Caseiro

IPC分类号： G10L15/19 ,  G06F17/28

CPC分类号： G10L15/08 ,  G06F17/289 ,  G10L15/19 ,  G10L15/197 ,  G10L25/54 ,  G10L2015/081 ,  G10L2015/228

摘要： Disclosed herein are systems, methods, and computer-readable storage media for a speech recognition application for directory assistance that is based on a user's spoken search query. The spoken search query is received by a portable device and portable device then determines its present location. Upon determining the location of the portable device, that information is incorporated into a local language model that is used to process the search query. Finally, the portable device outputs the results of the search query based on the local language model.

摘要翻译： 本文公开了用于基于用户的口语搜索查询的目录帮助的语音识别应用的系统，方法和计算机可读存储介质。 口头搜索查询由便携式设备接收，便携式设备随后确定其当前位置。 在确定便携式设备的位置时，该信息被并入用于处理搜索查询的本地语言模型中。 最后，便携式设备基于本地语言模型输出搜索查询的结果。

公开(公告)号：US08862582B2

公开(公告)日：2014-10-14

申请号：US11940703

申请日：2007-11-15

申请人： Charles Blewett ,  Enrico Bocchieri ,  Giuseppe Di Fabbrizio ,  Donnie Henderson ,  Thomas Killian ,  Thomas Kirk ,  David Kormann ,  Gregory T. Vesonder

发明人： Charles Blewett ,  Enrico Bocchieri ,  Giuseppe Di Fabbrizio ,  Donnie Henderson ,  Thomas Killian ,  Thomas Kirk ,  David Kormann ,  Gregory T. Vesonder

IPC分类号： G06F17/30 ,  G06K9/00

CPC分类号： G06F17/30864 ,  G06F17/30244 ,  G06F17/30265

摘要： Disclosed are a system, method and computer-readable medium for organizing images. A method aspect relates to receiving an image into a device, receiving incidental information associated with the image, organizing the image and the incidental information into a data structure such as a sparse array, classifying the received image with an image classifier and storing the classified image in an image database, receiving a search query and responding to the search query by searching for and retrieving matching images in the image database based on a comparison of the image search query to the data structure.

摘要翻译： 公开了一种用于组织图像的系统，方法和计算机可读介质。 方法方面涉及将图像接收到设备中，接收与图像相关联的附带信息，将图像和附带信息组织成诸如稀疏阵列的数据结构，使用图像分类器对接收到的图像进行分类并存储分类图像 在图像数据库中，基于图像搜索查询与数据结构的比较，通过搜索和检索图像数据库中的匹配图像来接收搜索查询并响应搜索查询。

公开(公告)号：US09484018B2

公开(公告)日：2016-11-01

申请号：US12952829

申请日：2010-11-23

申请人： Enrico Bocchieri ,  Dimitrios Dimitriadis ,  Horst J. Schroeter

发明人： Enrico Bocchieri ,  Dimitrios Dimitriadis ,  Horst J. Schroeter

IPC分类号： G10L15/06 ,  G10L15/065 ,  G10L15/30

CPC分类号： G10L15/063 ,  G10L15/065 ,  G10L15/30

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for building an automatic speech recognition system through an Internet API. A network-based automatic speech recognition server configured to practice the method receives feature streams, transcriptions, and parameter values as inputs from a network client independent of knowledge of internal operations of the server. The server processes the inputs to train an acoustic model and a language model, and transmits the acoustic model and the language model to the network client. The server can also generate a log describing the processing and transmit the log to the client. On the server side, a human expert can intervene to modify how the server processes the inputs. The inputs can include an additional feature stream generated from speech by algorithms in the client's proprietary feature extraction.

摘要翻译： 本文公开了用于通过因特网API构建自动语音识别系统的系统，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基于网络的自动语音识别服务器接收来自网络客户端的特征流，转录和参数值作为输入，而与服务器内部操作的知识无关。 服务器处理输入以训练声学模型和语言模型，并将声学模型和语言模型传输到网络客户端。 服务器还可以生成描述处理的日志，并将日志传送给客户端。 在服务器端，人类专家可以进行干预，以修改服务器如何处理输入。 输入可以包括通过客户端专有特征提取中的算法从语音生成的附加特征流。

公开(公告)号：US20090132467A1

公开(公告)日：2009-05-21

申请号：US11940703

申请日：2007-11-15

申请人： Charles Blewett ,  Enrico Bocchieri ,  Giuseppe Di Fabbrizio ,  Donnie Henderson ,  Thomas Killian ,  Thomas Kirk ,  David Kormann ,  Gregory T. Vesonder

发明人： Charles Blewett ,  Enrico Bocchieri ,  Giuseppe Di Fabbrizio ,  Donnie Henderson ,  Thomas Killian ,  Thomas Kirk ,  David Kormann ,  Gregory T. Vesonder

IPC分类号： G06F17/30

CPC分类号： G06F17/30864 ,  G06F17/30244 ,  G06F17/30265

摘要： Disclosed are a system, method and computer-readable medium for organizing images. A method aspect relates to receiving an image into a device, receiving incidental information associated with the image, organizing the image and the incidental information into a data structure such as a sparse array, classifying the received image with an image classifier and storing the classified image in an image database, receiving a search query and responding to the search query by searching for and retrieving matching images in the image database based on a comparison of the image search query to the data structure.

摘要翻译： 公开了一种用于组织图像的系统，方法和计算机可读介质。 方法方面涉及将图像接收到设备中，接收与图像相关联的附带信息，将图像和附带信息组织成诸如稀疏阵列的数据结构，使用图像分类器对接收到的图像进行分类并存储分类图像 在图像数据库中，基于图像搜索查询与数据结构的比较，通过搜索和检索图像数据库中的匹配图像来接收搜索查询并响应搜索查询。

公开(公告)号：US08914510B2

公开(公告)日：2014-12-16

申请号：US12272202

申请日：2008-11-17

申请人： Enrico Bocchieri ,  Horst Schroeter

发明人： Enrico Bocchieri ,  Horst Schroeter

IPC分类号： G06F15/16 ,  G06F15/173 ,  G06F11/00 ,  H04L29/08

CPC分类号： H04L67/22 ,  H04L67/14 ,  H04L67/142 ,  H04L67/146

摘要： A network communication system includes a connection server that assigns a network address within a data communication network to a subscriber terminal. The connection server receives outgoing communications from the subscriber terminal and transmits the outgoing communications to a network access point and receives incoming communications from the network access point and transmits the incoming communications to the subscriber terminal. The connection server intercepts a tracking cookie received from a remote server in the data communications network and intended for the subscriber terminal and stores the tracking cookie at the connection server so that the tracking cookie can be used to support a communication session between the subscriber terminal and the remote server without the tracking cookie being stored at the subscriber terminal.

摘要翻译： 网络通信系统包括将数据通信网络内的网络地址分配给用户终端的连接服务器。 连接服务器接收来自用户终端的出站通信，并将出局通信发送到网络接入点，并接收来自网络接入点的进入通信，并将进入的通信发送给用户终端。 连接服务器拦截从数据通信网络中的远程服务器接收的并且用于订户终端的跟踪cookie，并将跟踪cookie存储在连接服务器处，使得跟踪cookie可以用于支持用户终端和 没有跟踪cookie的远程服务器被存储在用户终端。

公开(公告)号：US20100125668A1

公开(公告)日：2010-05-20

申请号：US12272202

申请日：2008-11-17

申请人： Enrico Bocchieri ,  Horst Schroeter

发明人： Enrico Bocchieri ,  Horst Schroeter

IPC分类号： G06F15/16

CPC分类号： H04L67/22 ,  H04L67/14 ,  H04L67/142 ,  H04L67/146

摘要： A network communication system includes a connection server that assigns a network address within a data communication network to a subscriber terminal. The connection server receives outgoing communications from the subscriber terminal and transmits the outgoing communications to a network access point and receives incoming communications from the network access point and transmits the incoming communications to the subscriber terminal. The connection server intercepts a tracking cookie received from a remote server in the data communications network and intended for the subscriber terminal and stores the tracking cookie at the connection server so that the tracking cookie can be used to support a communication session between the subscriber terminal and the remote server without the tracking cookie being stored at the subscriber terminal.

摘要翻译： 网络通信系统包括将数据通信网络内的网络地址分配给用户终端的连接服务器。 连接服务器接收来自用户终端的出站通信，并将出局通信发送到网络接入点，并接收来自网络接入点的进入通信，并将进入的通信发送给用户终端。 连接服务器拦截从数据通信网络中的远程服务器接收的并且用于订户终端的跟踪cookie，并将跟踪cookie存储在连接服务器处，使得跟踪cookie可以用于支持用户终端和 没有跟踪cookie的远程服务器被存储在用户终端。

公开(公告)号：US4908865A

公开(公告)日：1990-03-13

申请号：US290816

申请日：1988-12-22

申请人： George R. Doddington ,  Enrico Bocchieri

发明人： George R. Doddington ,  Enrico Bocchieri

IPC分类号： G10L15/00

CPC分类号： G10L15/12

摘要： Recognition of sound units is improved by comparing frame-pair feature vectors which helps compensate for context variations in the pronunciation of sound units. A plurality of reference frames are stored of reference feature vectors representing reference words. A linear predictive coder (10) generates a plurality of spectral feature vectors for each frame of the speech signals. A filter bank system (12) transforms the spectral feature vectors to filter bank representations. A principal feature vector transformer (14) transforms the filter bank representations to an identity matrix of transformed input feature vectors. A concatenate frame system (16) concatenates the input feature vectors of adjacent frames to form the feature vector of a frame-pair. A transformer (18) and a comparator (20) compute the likelihood that each input feature vector for a frame-pair was produced by each reference frame. This computation is performed individually and independently for each reference frame-pairs. A dynamic time warper (22) constructs an optimum time path through the input speech signals for each of the computed likelihoods. A high level decision logic (24) recognizes the input speech signals as one of the reference words in response to the computed likelihoods and the optimum time paths.

摘要翻译： 通过比较有助于补偿声音单元发音的上下文变化的帧对特征向量来改善声音单元的识别。 存储表示参考词的参考特征向量的多个参考帧。 线性预测编码器（10）为每个语音信号帧生成多个频谱特征向量。 滤波器组系统（12）将频谱特征向量变换为滤波器组表示。 主要特征向量变换器（14）将滤波器组表示转换成变换的输入特征向量的单位矩阵。 级联帧系统（16）连接相邻帧的输入特征向量以形成帧对的特征向量。 变压器（18）和比较器（20）计算每对参考帧产生每一个帧对的输入特征向量的可能性。 对于每个参考帧对，单独且独立地执行该计算。 动态时间整形器（22）通过输入语音信号为每个计算出的可能性构建最佳时间路径。 高电平判定逻辑（24）响应于所计算的似然性和最佳时间路径将输入语音信号识别为参考词之一。