-
41.发明申请OPTIMIZATION OF NATURAL LANGUAGE PROCESSING SYSTEM BASED ON CONDITIONAL OUTPUT QUALITY AT RISK 有权基于条件输出质量风险的自然语言处理系统优化公开(公告)号：US20120253783A1
公开(公告)日：2012-10-04
申请号：US13073255
申请日：2011-03-28
申请人： Vittorio Castelli , David Nahamoo , Bing Zhao
发明人： Vittorio Castelli , David Nahamoo , Bing Zhao
CPC分类号： G06F17/2818 , G06F17/2854
摘要： Techniques are disclosed for optimizing results output by a natural language processing system. For example, a method comprises optimizing one or more parameters of a natural language processing system so as to improve a measure of quality of an output of the natural language processing system for a first type of data processed by the natural language processing system while maintaining a given measure of quality of an output of the natural language processing system for a second type of data processed by the natural language processing system. For example, the first type of data may have a substantive complexity that is greater than that of the second type of data. Thus, when the natural language processing system is a machine translation system, use of a conditional value at risk metric for the translation quality provides for a high quality output of the machine translation system for data of a high substantive complexity (for sophisticated users) while maintaining an average quality output for average data (for average users).
摘要翻译： 公开了用于优化由自然语言处理系统输出的结果的技术。 例如，一种方法包括优化自然语言处理系统的一个或多个参数，以便改善对于由自然语言处理系统处理的第一类型的数据的自然语言处理系统的输出的质量的量度，同时保持 给出自然语言处理系统对自然语言处理系统处理的第二类数据的输出质量的度量。 例如，第一类型的数据可能具有大于第二类型的数据的实质性复杂度。 因此，当自然语言处理系统是机器翻译系统时，使用翻译质量的风险度量条件值为机器翻译系统提供高质量的高实质性复杂性（针对复杂用户）的数据输出，同时 维持平均数据（平均用户）的平均质量输出。
-
公开(公告)号：US20120239387A1
公开(公告)日：2012-09-20
申请号：US13049924
申请日：2011-03-17
申请人： Shay Ben-David , Ron Hoory , Zvi Kons , David Nahamoo
发明人： Shay Ben-David , Ron Hoory , Zvi Kons , David Nahamoo
IPC分类号： G10L19/02
CPC分类号： G10L21/003 , G10L19/018
摘要： Method, system, and computer program product for voice transformation are provided. The method includes transforming a source speech using transformation parameters, and encoding information on the transformation parameters in an output speech using steganography, wherein the source speech can be reconstructed using the output speech and the information on the transformation parameters. A method for reconstructing voice transformation is also provided including: receiving an output speech of a voice transformation system wherein the output speech is transformed speech which has encoded information on the transformation parameters using steganography; extracting the information on the transformation parameters; and carrying out an inverse transformation of the output speech to obtain an approximation of an original source speech.
摘要翻译： 提供语音转换的方法，系统和计算机程序产品。 该方法包括使用变换参数来变换源语言，以及使用隐写术对输入语音中的变换参数对信息进行编码，其中可以使用输出语音和关于变换参数的信息来重构源语音。 还提供了一种用于重建语音变换的方法，包括：接收语音转换系统的输出语音，其中输出语音是使用隐写术编码关于变换参数的信息的变换语音; 提取变换参数信息; 并执行输出语音的逆变换以获得原始源语音的近似。
-
公开(公告)号：US20110304446A1
公开(公告)日：2011-12-15
申请号：US12814429
申请日：2010-06-11
CPC分类号： H04W48/04 , B60K28/063 , B60W2540/28
摘要： Techniques for preventing a driver of a moving vehicle from using a handheld device while driving. An example system of the invention includes a plurality of biometric sensors configured to receive biometric data from the driver and a user of the handheld device. Contemporaneously with operation of the vehicle and the handheld device, the biometric data is analyzed in order to determine a match between the identity of the vehicle driver and the user of the handheld device. A controller is configured to selectively interrupt operation of the vehicle or handheld device upon detecting the match.
摘要翻译： 用于在驾驶时防止移动车辆的驾驶员使用手持装置的技术。 本发明的示例性系统包括被配置为从驾驶员和手持设备的用户接收生物测定数据的多个生物测定传感器。 与车辆和手持设备的操作同时，分析生物特征数据，以便确定车辆驾驶员的身份与手持设备的用户之间的匹配。 控制器被配置为在检测到匹配时选择性地中断车辆或手持设备的操作。
-
公开(公告)号：US07137126B1
公开(公告)日：2006-11-14
申请号：US09806565
申请日：1999-10-01
申请人： Daniel Coffman , Liam D. Comerford , Steven DeGennaro , Edward A. Epstein , Ponani Gopalakrishnan , Stephane H. Maes , David Nahamoo
发明人： Daniel Coffman , Liam D. Comerford , Steven DeGennaro , Edward A. Epstein , Ponani Gopalakrishnan , Stephane H. Maes , David Nahamoo
CPC分类号： H04M3/50 , G06F17/30899 , G10L15/22 , G10L15/285 , G10L2015/228 , H04L67/02 , H04M1/72561 , H04M3/42204 , H04M3/44 , H04M3/493 , H04M3/4931 , H04M3/4936 , H04M3/4938 , H04M7/00 , H04M2201/40 , H04M2201/60 , H04M2203/355 , H04M2250/74
摘要： A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) (10) across a plurality of conversationally aware applications (11) (i.e., applications that “speak” conversational protocols) and conventional applications (12). The conversationally aware maps, applications (11) communicate with a conversational kernel (14) via conversational application APIs (13). The conversational kernel (14) controls the dialog across applications and devices (local and networked) on the basis of their registered conversational capabilities and requirements and provides a unified conversational user interface and conversational services and behaviors. The conversational computing system may be built on top of a conventional operating system and APIs (15) and conventional device hardware (16). The conversational kernel (14) handles all I/O processing and controls conversational engines (18). The conversational kernel (14) converts voice requests into queries and converts outputs and results into spoken messages using conversational engines (18) and conversational arguments (17). The conversational application API (13) conveys all the information for the conversational kernel (14) to transform queries into application calls and conversely convert output into speech, appropriately sorted before being provided to the user.
摘要翻译： 一种对话计算系统，其跨越多个会话感知应用（11）（即，“说”对话协议的应用“）和常规应用（12）提供通用协调多模态对话用户界面（CUI）（10）。 对话感知地图，应用程序（11）通过对话应用程序API（13）与对话内核（14）进行通信。 对话内核（14）根据其注册的会话能力和要求，控制应用和设备（本地和网络）之间的对话，并提供统一的会话用户界面和对话服务和行为。 对话计算系统可以构建在常规操作系统和API（15）和常规设备硬件（16）之上。 对话内核（14）处理所有I / O处理和控制对话引擎（18）。 会话内核（14）将语音请求转换为查询，并将会话引擎（18）和会话参数（17）将输出和结果转换为口语消息。 对话应用程序API（13）传达对话内核（14）的所有信息，以将查询转换成应用程序调用，并相反地将输出转换为语音，在提供给用户之前进行适当排序。
-
公开(公告)号：US06748361B1
公开(公告)日：2004-06-08
申请号：US09460077
申请日：1999-12-14
IPC分类号： G10L1522
CPC分类号： G10L15/28
摘要： A Personal Speech Assistant (PSA) is a computing apparatus which provides a spoken language interface to another apparatus to which it is attached by supporting execution of a conversational dialog manager and its supporting service engines. In operation, a PSA is connected to a device which provides some service to a user. Any “appliance” is a candidate for enhancement with the PSA. Devices such as, for example, video cassette recorders (VCRs) or Personal Digital Assistants (PDAs), which offer rich, but frequently difficult interfaces, may be made more useful by the integration of a PSA according to the invention. It is a preferred feature of a dialog manager used by the PSA that the user interface properties, in terms of the vocabulary the device understands, the informative prompts it provides, and other aspects of its conversational behavior, are all easily modified to correspond to the preferences or limitations of the user.
摘要翻译： 个人语音助理（PSA）是一种通过支持会话对话管理器及其支持服务引擎的执行来向附加的另一设备提供口语语言接口的计算设备。 在操作中，PSA连接到向用户提供一些服务的设备。 任何“家电”都是使用PSA进行增强的候选人。 通过集成根据本发明的PSA，可提供诸如例如提供丰富而且经常困难的界面的诸如录像机（VCR）或个人数字助理（PDA）的设备更有用。 PSA使用的对话管理器的优选特征是，用户接口属性（根据设备理解的词汇表），其提供的信息提示以及其会话行为的其他方面都是容易地被修改为对应于 用户的偏好或限制。
-
公开(公告)号：US06219638B1
公开(公告)日：2001-04-17
申请号：US09185332
申请日：1998-11-03
IPC分类号： G10L1508
CPC分类号： H04M3/53366 , G10L15/22 , G10L2015/221 , H04M3/5307 , H04M2201/40 , H04M2201/60
摘要： A messaging system for receiving speech over a telephone and converting the speech to text includes a first server for receiving speech input by a user, a speech recognition system for converting the speech to text, a speech synthesizer for converting the text to speech for playing back the synthesized speech for correction by the user and a correction mechanism for enabling the user to correct the speech such that the corrected speech is provided as text for transmittal over a communication system.
摘要翻译： 一种用于通过电话接收语音并将语音转换为文本的消息系统包括用于接收用户输入的语音的第一服务器，用于将语音转换为文本的语音识别系统，用于将文本转换为语音以进行回放的语音合成器 用于用户校正的合成语音和用于使用户能够校正语音的校正机制，使得校正的语音被提供为用于通过通信系统传送的文本。
-
47.发明授权Speech coding via speech recognition and synthesis based on pre-enrolled phonetic tokens 失效基于预先录入的语音标记的语音识别和综合语音编码
公开(公告)号：US6119086A
公开(公告)日：2000-09-12
申请号：US67863
申请日：1998-04-28
CPC分类号： G10L19/0018
摘要： A speech coding system, responsive to an input speech signal provided by a system user, comprises: a speech coding portion including a speech recognition system responsive to the input speech signal and having a word vocabulary associated therewith, the speech recognition system recognizing the input speech signal in accordance with the vocabulary and generating phonetic tokens, such as at least one sequence of lefemes, representative of the input speech signal; a channel, responsive to the at least one sequence of lefemes, for transmitting and/or storing the at least one sequence of lefemes; and a speech synthesizing portion, responsive to the transmitted/stored sequence of lefemes, for generating a synthesized speech signal which is representative of the input speech signal provided by the system user using the at least one sequence of lefemes. The speech recognition system preferably generates acoustic parameters from the input speech signal which include voice characteristics of the system user. The speech coding system also preferably comprises a labeler which processes the input speech signal including words uttered by the system user which are not in the word vocabulary associated with the speech recognition system, the labeler generating phonetic tokens, such as at least one sequence of lefemes, optimally representative of the input speech signal. The sequence of lefemes from the labeler and the speech recognition portion are compared, for each speech segment, and the sequence most similar to the input speech is selected for transmission/storage. The speech synthesizing portion of the system preferably performs speech synthesis using pre-enrolled phonetic sub-units or tokens.
摘要翻译： 响应于由系统用户提供的输入语音信号的语音编码系统包括：语音编码部分，包括响应于输入语音信号并具有与其相关联的词汇词汇的语音识别系统，语音识别系统识别输入语音 信号，并产生语音令牌，例如表示输入语音信号的至少一个左派序列; 响应于所述至少一个左列的序列的信道，用于发送和/或存储所述至少一个左派序列; 以及语音合成部分，响应于所发送/存储的莱佛斯序列，用于产生代表由系统用户使用至少一个左派序列提供的输入语音信号的合成语音信号。 语音识别系统优选地从包括系统用户的语音特征的输入语音信号生成声学参数。 语音编码系统还优选地包括标签器，其处理包括不在与语音识别系统相关联的词汇词汇中的由系统用户发出的单词的输入语音信号，产生语音令牌的标签器，例如至少一个lefemes序列 ，最佳地代表输入语音信号。 对于每个语音段，比较来自标签机和语音识别部分的左派序列，并且选择与输入语音最相似的序列用于传输/存储。 系统的语音合成部分优选地使用预先注册的语音子单元或令牌来执行语音合成。
-
48.发明授权Continuous parameter hidden Markov model approach to automatic handwriting recognition 失效连续参数隐马尔可夫模型法自动手写识别
公开(公告)号：US5636291A
公开(公告)日：1997-06-03
申请号：US467615
申请日：1995-06-06
CPC分类号： G06K9/6297
摘要： A computer-based system and method for recognizing handwriting. The present invention includes a pre-processor, a front end, and a modeling component. The present invention operates as follows. First, the present invention identifies the lexemes for all characters of interest. Second, the present invention performs a training phase in order to generate a hidden Markov model for each of the lexemes. Third, the present invention performs a decoding phase to recognize handwritten text. Hidden Markov models for lexemes are produced during the training phase. The present invention performs the decoding phase as follows. The present invention receives test characters to be decoded (that is, to be recognized). The present invention generates sequences of feature vectors for the test characters by mapping in chirographic space. For each of the test characters, the present invention computes probabilities that the test character can be generated by the hidden Markov models. The present invention decodes the test character as the recognized character associated with the hidden Markov model having the greatest probability.
摘要翻译： 一种用于识别笔迹的基于计算机的系统和方法。 本发明包括预处理器，前端和建模组件。 本发明如下操作。 首先，本发明识别所有感兴趣的人物的词汇。 第二，本发明执行训练阶段，以便为每个词汇生成隐马尔可夫模型。 第三，本发明执行解码阶段来识别手写文本。 训练阶段产生了隐马尔可夫模型。 本发明如下进行解码阶段。 本发明接收要解码的测试字符（即将被识别）。 本发明通过在手写空间中映射来生成用于测试字符的特征向量的序列。 对于每个测试字符，本发明计算由隐马尔可夫模型可以产生测试字符的概率。 本发明将测试字符解码为与具有最大概率的隐马尔可夫模型相关联的识别字符。
-
公开(公告)号：US5343537A
公开(公告)日：1994-08-30
申请号：US785642
申请日：1991-10-31
CPC分类号： G06K9/6217 , G06K9/00416 , G06K9/00429
摘要： Method and apparatus for automatic recognition of handwritten text based on a suitable representation of handwriting in one or several feature vector spaces(s), Gaussian modeling in each space, and mixture decoding to take into account the contribution of all relevant prototypes in all spaces. The feature vector space(s) is selected to encompass both a local and a global description of each appropriate point on a pen trajectory. Windowing is performed to capture broad trends in the handwriting, after which a linear transformation is applied to suitably eliminate redundancy. The resulting feature vector space(s) is called chirographic space(s). Gaussian modeling is performed to isolate adequate chirographic prototype distributions in each space, and the mixture coefficients weighting these distributions are trained using a maximum likelihood framework. Decoding can be performed simply and effectively by accumulating the contribution of all relevant prototype distributions. Post-processing using a language model may be included.
摘要翻译： 基于在一个或多个特征向量空间中的手写的适当表示，每个空间中的高斯建模，以及混合解码，以便考虑所有空间中所有相关原型的贡献，自动识别手写文本的方法和装置。 选择特征向量空间以包含笔轨迹上的每个适当点的局部和全局描述。 执行窗口以捕获手写的广泛趋势，之后应用线性变换以适当地消除冗余。 所得到的特征向量空间称为手绘空间。 执行高斯建模以分离每个空间中的足够的手写原型分布，并且使用最大似然框架训练对这些分布加权的混合系数。 通过积累所有相关原型分布的贡献，可以简单有效地执行解码。 可以包括使用语言模型的后处理。
-
50.发明授权Fast algorithm for deriving acoustic prototypes for automatic speech recognition 失效用于自动语音识别的声学原型的快速算法
公开(公告)号：US5276766A
公开(公告)日：1994-01-04
申请号：US730714
申请日：1991-07-16
CPC分类号： G10L15/063
摘要： An apparatus for generating a set of acoustic prototype signals for encoding speech includes a memory for storing a training script model comprising a series of word-segment models. Each word-segment model comprises a series of elementary models. An acoustic measure is provided for measuring the value of at least one feature of an utterance of the training script during each of a series of time intervals to produce a series of feature vector signals representing the feature values of the utterance. An acoustic matcher is provided for estimating at least one path through the training script model which would produce the entire series of measured feature vector signals. From the estimated path, the elementary model in the training script model which would produce each feature vector signal is estimated. The apparatus further comprises a cluster processor for clustering the feature vector signals into a plurality of clusters. Each feature vector signal in a cluster corresponds to a single elementary model in a single location in a single word-segment model. Each cluster signal has a cluster value equal to an average of the feature values of all feature vectors in the signal. Finally, the apparatus includes a memory for storing a plurality of prototype vector signals. Each prototype vector signal corresponds to an elementary model, has an identifier, and comprises at least two partition values. The partition values are equal to combinations of the cluster values of one or more cluster signals corresponding to the elementary model.
摘要翻译： 一种用于生成用于编码语音的声原型信号的集合的装置包括用于存储包括一系列字段模型的训练脚本模型的存储器。 每个单词段模型包括一系列基本模型。 提供了一种声学测量，用于在一系列时间间隔的每一个期间测量训练脚本的发音的至少一个特征的值，以产生表示发音的特征值的一系列特征向量信号。 提供声学匹配器用于估计通过训练脚本模型的至少一个路径，其将产生整个测量的特征向量信号的一系列。 从估计的路径，估计将产生每个特征向量信号的训练脚本模型中的基本模型。 该装置还包括用于将特征向量信号聚类成多个聚类的聚类处理器。 群集中的每个特征向量信号对应于单个单词段模型中单个位置中的单个基本模型。 每个聚类信号具有等于信号中所有特征向量的特征值的平均值的聚类值。 最后，该装置包括用于存储多个原型矢量信号的存储器。 每个原型矢量信号对应于基本模型，具有标识符，并且包括至少两个分区值。 分区值等于对应于基本模型的一个或多个聚类信号的聚类值的组合。
-
-
-
-
-
-
-
-
-
搜索结果
81 条记录 (耗时 0.032 秒)
