利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

23 条记录 (耗时 0.022 秒)

    Specific task composite acoustic models
    1.
    发明授权
    Specific task composite acoustic models 有权
    具体任务复合声学模型

    公开(公告)号：US06260014B1

    公开(公告)日：2001-07-10

    申请号：US09153222

    申请日：1998-09-14

    申请人： Lalit Rai Bahl ,  David Lubensky ,  Mukund Padmanabhan ,  Salim Roukos

    发明人： Lalit Rai Bahl ,  David Lubensky ,  Mukund Padmanabhan ,  Salim Roukos

    IPC分类号： G10L1504

    CPC分类号： G10L15/26 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/228

    摘要： A method for recognizing speech includes the steps of providing a generic model having a baseform representation of a vocabulary of words, identifying a subset of words relating to an application, constructing a task specific model for the subset of words, constructing a composite model by combining the generic and task specific models and modifying the baseform representation of the subset of words such that the subset of words are recognized by the task specific model. A system for recognizing speech includes a composite model having a generic model having a generic baseform representation of a vocabulary of words and a task specific model for recognizing a subset of words relating to an application wherein the subset of words are recognized using a modified baseform representation. A recognizer compares words input thereto with the generic model for words other than the subset of words and with the task specific model for the subset of words.

    摘要翻译： 一种用于识别语音的方法包括以下步骤：提供具有词汇词典的基本形式表示的通用模型，识别与应用有关的单词的子集，为所述单词子集构建任务特定模型，通过组合来构建复合模型 通用和任务特定模型，并修改单词子集的基本形式表示，使得单词的子集由任务特定模型识别。 用于识别语音的系统包括具有通用模型的复合模型，所述通用模型具有词汇词典的通用基本形式表示，以及用于识别与应用有关的词组的任务特定模型，其中使用经修改的基本形式表示来识别单词的子集 。 识别器将输入的词与除单词子集之外的单词的通用模型和词语子集的任务特定模型进行比较。

    Unsupervised incremental adaptation using maximum likelihood spectral transformation
    3.
    发明申请
    Unsupervised incremental adaptation using maximum likelihood spectral transformation 有权
    使用最大似然谱变换的无监督增量自适应

    公开(公告)号：US20060009972A1

    公开(公告)日：2006-01-12

    申请号：US11215415

    申请日：2005-08-30

    申请人： Dongsuk Yuk ,  David Lubensky

    发明人： Dongsuk Yuk ,  David Lubensky

    IPC分类号： G10L19/14

    CPC分类号： G10L15/065 ,  G10L15/20 ,  G10L21/0216

    摘要： In a speech recognition system, a method of transforming speech feature vectors associated with speech data provided to the speech recognition system includes the steps of receiving likelihood of utterance information corresponding to a previous feature vector transformation, estimating one or more transformation parameters based, at least in part, on the likelihood of utterance information corresponding to a previous feature vector transformation, and transforming a current feature vector based on maximum likelihood criteria and/or the estimated transformation parameters, the transformation being performed in a linear spectral domain. The step of estimating the one or more transformation parameters includes the step of estimating convolutional noise Niα and additive noise Niβ for each ith component of a speech vector corresponding to the speech data provided to the speech recognition system.

    摘要翻译： 在语音识别系统中，将与提供给语音识别系统的语音数据相关联的语音特征矢量变换的方法包括以下步骤：接收与先前的特征向量变换相对应的话语信息的可能性，至少基于至少估计一个或多个变换参数 部分地基于与先前的特征向量变换相对应的发声信息的可能性，并且基于最大似然准则和/或估计的变换参数来变换当前特征向量，在线性频域中执行变换。 估计一个或多个变换参数的步骤包括以下步骤：估计卷积噪声N＆lt;α＆gt;和加性噪声N＆lt; 对应于提供给语音识别系统的语音数据的语音向量的每个第i个分量的。

    Game based method for translation data acquisition and evaluation
    4.
    发明授权
    Game based method for translation data acquisition and evaluation 有权
    基于游戏的翻译数据采集和评估方法

    公开(公告)号：US08566078B2

    公开(公告)日：2013-10-22

    申请号：US12697047

    申请日：2010-01-29

    申请人： Ruhi Sarikaya ,  Jiri Navratil ,  Osamuyimen Stewart ,  David Lubensky

    发明人： Ruhi Sarikaya ,  Jiri Navratil ,  Osamuyimen Stewart ,  David Lubensky

    IPC分类号： G06F17/28 ,  G10L15/00 ,  G10L15/26 ,  G10L15/06 ,  G10L13/00 ,  G10L13/08 ,  G10L21/00

    CPC分类号： A63F9/24 ,  G06F17/28

    摘要： A method of generating a statistical machine translation database through a game in which a monolingual structure is provided to a plurality of players. A first translation attempt is received from each of the plurality of players. The first translation attempt from each of the plurality of players is compared. Feedback is provided to each of the plurality of players and the attempts are received and compared to provide feedback to iteratively converge subsequent translations from each of the plurality of players into a final translated structure.

    摘要翻译： 一种通过游戏产生统计机器翻译数据库的方法，其中向多个玩家提供单语构造。 从多个玩家中的每一个接收第一翻译尝试。 比较来自多个玩家中的每一个的第一翻译尝试。 向多个玩家中的每一个提供反馈，并且尝试被接收并且进行比较以提供反馈以迭代地收敛从多个玩家中的每一个到随后的翻译结构的后续翻译。

    Open architecture based domain dependent real time multi-lingual communication service
    6.
    发明授权
    Open architecture based domain dependent real time multi-lingual communication service 有权
    基于开放架构的域依赖实时多语言通信服务

    公开(公告)号：US08270606B2

    公开(公告)日：2012-09-18

    申请号：US12113567

    申请日：2008-05-01

    申请人： Sasha Porto Caskey ,  Danning Jiang ,  Wen Liu ,  David Lubensky ,  Yong Qin ,  Andrzej Sakrajda ,  Cheng Wu

    发明人： Sasha Porto Caskey ,  Danning Jiang ,  Wen Liu ,  David Lubensky ,  Yong Qin ,  Andrzej Sakrajda ,  Cheng Wu

    IPC分类号： H04L29/12

    CPC分类号： G06F17/289 ,  H04L63/0442 ,  H04L63/104

    摘要： A system and method for real-time network communications provides a session identifier as a public key for group communication between clients, and provides a channel identifier representing a private key for each of a plurality of clients. The channel identifier includes client-specific attributes, which function to indicate grouping criteria for the group communication. A dynamic communication link is created over a network between a client and a service based upon the public and private key combination such that group communication is enabled based upon the attributes of the private key and the public key. Communications are translated using a translation service which employs the attributes associated with the private key and the public key combination to provide response information in a designated language to enable multi-lingual real-time communications.

    摘要翻译： 用于实时网络通信的系统和方法提供会话标识符作为用于客户端之间的组通信的公钥，并且为多个客户端中的每一个提供表示私钥的信道标识符。 信道标识符包括特定于客户端的属性，其用于指示组通信的分组标准。 基于公共和私人密钥组合，在客户端和服务之间的网络上创建动态通信链路，使得基于私钥和公钥的属性启用组通信。 使用使用与私钥和公钥组合相关联的属性的翻译服务来翻译通信，以提供指定语言的响应信息以实现多语言实时通信。

    Method and apparatus for handset detection
    8.
    发明授权
    Method and apparatus for handset detection 有权
    手机检测方法及装置

    公开(公告)号：US06778957B2

    公开(公告)日：2004-08-17

    申请号：US09934157

    申请日：2001-08-21

    申请人： Zhong-Hua Wang ,  David Lubensky ,  Cheng Wu

    发明人： Zhong-Hua Wang ,  David Lubensky ,  Cheng Wu

    IPC分类号： G10L1510

    CPC分类号： G10L17/02 ,  G10L17/20

    摘要： Disclosed is a method of automated handset identification, comprising receiving a sample speech input signal from a sample handset; deriving a cepstral covariance sample matrix from said first sample speech signal; calculating, with a distance metric, all distances between said sample matrix and one or more cepstral covariance handset matrices, wherein each said handset matrix is derived from a plurality of speech signals taken from different speakers through the same handset; and determining if the smallest of said distances is below a predetermined threshold value.

    摘要翻译： 公开了一种自动化手机识别的方法，包括从样本手机接收样本语音输入信号; 从所述第一样本语音信号导出倒谱协方差样本矩阵; 用距离度量计算所述样本矩阵与一个或多个倒谱协方差手机矩阵之间的所有距离，其中每个所述手机矩阵从通过相同手机从不同扬声器取得的多个语音信号导出; 以及确定所述距离中的最小值是否低于预定阈值。