公开(公告)号：US08812321B2

公开(公告)日：2014-08-19

申请号：US12895359

申请日：2010-09-30

Applicant: Mazin Gilbert ,  Srinivas Bangalore ,  Patrick Haffner ,  Robert Bell

Inventor： Mazin Gilbert ,  Srinivas Bangalore ,  Patrick Haffner ,  Robert Bell

IPC: G10L15/08 ,  G10L15/32

CPC classification number: G10L15/32 ,  G10L15/063 ,  G10L15/26 ,  G10L2015/0638

Abstract: Disclosed herein are systems, methods and non-transitory computer-readable media for performing speech recognition across different applications or environments without model customization or prior knowledge of the domain of the received speech. The disclosure includes recognizing received speech with a collection of domain-specific speech recognizers, determining a speech recognition confidence for each of the speech recognition outputs, selecting speech recognition candidates based on a respective speech recognition confidence for each speech recognition output, and combining selected speech recognition candidates to generate text based on the combination.

Abstract translation: 本文公开了用于在不需要模型定制或接收到的语音的领域的先前知识的情况下在不同的应用或环境上执行语音识别的系统，方法和非暂时的计算机可读介质。 该公开内容包括：利用特定领域的语音识别器的集合来识别接收的语音，为每个语音识别输出确定语音识别置信度，基于每个语音识别输出的相应的语音识别置信度选择语音识别候选，以及组合所选语音 识别候选人基于组合生成文本。

公开(公告)号：US08600744B2

公开(公告)日：2013-12-03

申请号：US13446329

申请日：2012-04-13

Applicant: Mazin Gilbert

Inventor： Mazin Gilbert

IPC: G10L15/06

CPC classification number: G10L15/07

Abstract: Disclosed are systems, methods, and computer readable media for performing speech recognition. The method embodiment comprises selecting a codebook from a plurality of codebooks with a minimal acoustic distance to a received speech sample, the plurality of codebooks generated by a process of (a) computing a vocal tract length for a each of a plurality of speakers, (b) for each of the plurality of speakers, clustering speech vectors, and (c) creating a codebook for each speaker, the codebook containing entries for the respective speaker's vocal tract length, speech vectors, and an optional vector weight for each speech vector, (2) applying the respective vocal tract length associated with the selected codebook to normalize the received speech sample for use in speech recognition, and (3) recognizing the received speech sample based on the respective vocal tract length associated with the selected codebook.

Abstract translation: 公开了用于执行语音识别的系统，方法和计算机可读介质。 方法实施例包括从具有对接收到的语音样本的最小声距离的多个码本中选择码本，所述多个码本通过（a）计算多个扬声器中的每一个的声道长度的处理而生成（ b）对于所述多个扬声器中的每一个，聚类语音向量，以及（c）为每个说话者创建码本，所述码本包含用于每个语音向量的相应说话者声道长度，语音向量和可选矢量权重的条目， （2）应用与所选码本相关联的相应声道长度，以规范化用于语音识别的接收到的语音样本，以及（3）基于与所选码本相关联的相应声道长度来识别所接收的语音样本。

公开(公告)号：US08589163B2

公开(公告)日：2013-11-19

申请号：US12631111

申请日：2009-12-04

Applicant: Andrej Ljolje ,  Mazin Gilbert

Inventor： Andrej Ljolje ,  Mazin Gilbert

IPC: G10L15/06 ,  G10L15/12 ,  G10L15/22

CPC classification number: G10L15/183 ,  G10L2015/227 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for performing speech recognition based on a masked language model. A system configured to practice the method receives a masked language model including a plurality of words, wherein a bit mask identifies whether each of the plurality of words is allowed or disallowed with regard to an adaptation subset, receives input speech, generates a speech recognition lattice based on the received input speech using the masked language model, removes from the generated lattice words identified as disallowed by the bit mask for the adaptation subset, and recognizes the received speech based on the lattice. Alternatively during the generation step, the system can only add words indicated as allowed by the bit mask. The bit mask can be separate from or incorporated as part of the masked language model. The system can dynamically update the adaptation subset and bit mask.

Abstract translation: 本文公开了用于基于掩蔽语言模型执行语音识别的系统，方法和计算机可读存储介质。 被配置为实施该方法的系统接收包括多个单词的掩蔽语言模型，其中位掩码识别关于自适应子集是否允许或不允许多个单词中的每一个，接收输入语音，生成语音识别格 基于使用掩蔽语言模型的接收到的输入语音，从由适配子集的位掩码识别为不允许的生成的格子字中移除，并且基于格子识别接收的语音。 或者在生成步骤期间，系统只能添加由位掩码允许的指示的字。 位掩码可以与掩蔽语言模型的一部分分开或并入。 系统可以动态地更新自适应子集和位掩码。

公开(公告)号：US08433558B2

公开(公告)日：2013-04-30

申请号：US11188825

申请日：2005-07-25

Applicant: Srinivas Bangalore ,  Mazin Gilbert ,  Narendra K. Gupta

Inventor： Srinivas Bangalore ,  Mazin Gilbert ,  Narendra K. Gupta

IPC: G06F17/20 ,  G06F17/27 ,  G06F17/21 ,  G10L15/28 ,  G10L15/18 ,  G10L15/14 ,  G10L21/00

CPC classification number: G10L15/183 ,  G06F17/2818 ,  G10L15/14 ,  G10L15/19

Abstract: Disclosed herein are systems and methods to incorporate human knowledge when developing and using statistical models for natural language understanding. The disclosed systems and methods embrace a data-driven approach to natural language understanding which progresses seamlessly along the continuum of availability of annotated collected data, from when there is no available annotated collected data to when there is any amount of annotated collected data.

Abstract translation: 这里公开的是在开发和使用自然语言理解的统计模型时将人类知识结合在一起的系统和方法。 所公开的系统和方法包含一种数据驱动的自然语言理解方法，其从注释收集的数据的可用性的连续性无缝地进行，从没有可用的注释收集的数据到当有任何数量的注释收集的数据时。

公开(公告)号：US08296140B2

公开(公告)日：2012-10-23

申请号：US13300752

申请日：2011-11-21

Applicant: Srinivas Bangalore ,  Mazin Gilbert ,  Narendra Gupta

Inventor： Srinivas Bangalore ,  Mazin Gilbert ,  Narendra Gupta

IPC: G10L15/00

CPC classification number: G06F17/2785

Abstract: In accordance with one aspect of the present invention, an automated method of and system for generating a response to a text-based natural language message is disclosed. The method includes identifying a first selected input clause in a sentence in the text-based natural language message. Also, assigning a semantic tag to the first selected input clause and matching the semantic tag to a historical input tag. The historical input tag associated with a first previously generated response clause. Further; generating an output response message based on the historical response clause, the output response message derived from the historical input tag and a second previously generated response clause. The system includes means for performing the method steps.

Abstract translation: 根据本发明的一个方面，公开了一种用于生成对基于文本的自然语言消息的响应的自动化方法和系统。 该方法包括识别基于文本的自然语言消息中的句子中的第一选择的输入子句。 此外，将语义标签分配给第一选择的输入子句并将语义标签与历史输入标签进行匹配。 与先前生成的第一个响应子句相关联的历史输入标签。 进一步; 基于历史响应子句生成输出响应消息，从历史输入标签导出的输出响应消息和第二个先前生成的响应子句。 该系统包括用于执行方法步骤的装置。

公开(公告)号：US20120084081A1

公开(公告)日：2012-04-05

申请号：US12895337

申请日：2010-09-30

Applicant: ILYA Dan MELAMED ,  Mazin Gilbert

Inventor： ILYA Dan MELAMED ,  Mazin Gilbert

IPC: G10L21/00

CPC classification number: G06N7/005 ,  G06F17/30684 ,  G06Q30/01

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing trend analysis of speech. A system practicing the method receives a speech trend analysis request having candidate feature constraints, an objective function with respect to a speech trend to be analyzed, and a set of speech record constraints. The system selects a subset of speech records from the group of speech records based on the set of speech record constraints to yield selected speech records, identifies features in the selected speech records based on the set of candidate feature constraints to yield identified features, and assigns a weight to each of the identified features based on the objective function. Then the system ranks the identified features by their respective weights to yield ranked identified features, and outputs at least one of the ranked identified features associated with a speech-based trend in response to the speech trend analysis request.

Abstract translation: 这里公开了用于执行语音趋势分析的系统，方法和非暂时的计算机可读存储介质。 实施该方法的系统接收具有候选特征约束的语音趋势分析请求，关于待分析的语音趋势的目标函数和一组语音记录约束。 该系统基于语音记录约束集从语音记录组中选择语音记录的子集，以产生所选择的语音记录，基于候选特征约束集来识别所选语音记录中的特征，以产生所识别的特征，并且分配 基于目标函数对每个识别的特征的权重。 然后，系统通过它们各自的权重对所识别的特征进行排序，以产生排名确定的特征，并响应于语音趋势分析请求输出与基于语音的趋势相关联的排名确定的特征中的至少一个。

公开(公告)号：US08082151B2

公开(公告)日：2011-12-20

申请号：US11857036

申请日：2007-09-18

Applicant: Srinivas Bangalore ,  Mazin Gilbert ,  Narendra Gupta

Inventor： Srinivas Bangalore ,  Mazin Gilbert ,  Narendra Gupta

IPC: G10L15/00

CPC classification number: G06F17/2785

Abstract: In accordance with one aspect of the present invention, an automated method of and system for generating a response to a text-based natural language message is disclosed. The method includes identifying a sentence in the text-based natural language message. Also, identifying an input clause in the sentence. Further, comparing the input clause to a previously received clause, where the previously received clause is correlated with a previously generated response message. Additionally, generating an output response message based on the previously generated response message. The system includes means for performing the method steps.

Abstract translation: 根据本发明的一个方面，公开了一种用于生成对基于文本的自然语言消息的响应的自动化方法和系统。 该方法包括识别基于文本的自然语言消息中的句子。 另外，确定句子中的一个input子句。 此外，将输入子句与先前接收的子句进行比较，其中先前接收的子句与先前生成的响应消息相关联。 另外，基于先前生成的响应消息生成输出响应消息。 该系统包括用于执行方法步骤的装置。

公开(公告)号：US20110258531A1

公开(公告)日：2011-10-20

申请号：US13088935

申请日：2011-04-18

Applicant: Srinivas Bangalore ,  Junlan Feng ,  Mazin Gilbert ,  Jay Gordon Wilpon

Inventor： Srinivas Bangalore ,  Junlan Feng ,  Mazin Gilbert ,  Jay Gordon Wilpon

IPC: G06F17/00

CPC classification number: G06F17/2235 ,  G06Q30/02 ,  G06Q30/06

Abstract: A website mining tool is disclosed that extracts information from, for example, a company's website and presents the extracted information in a graphical user interface (GUI). In one embodiment, web pages from a website are stored in, for example, computer memory and a structure of the web pages is identified. A plurality of blocks of information is then extracted as a function of this structure and a category is assigned to each block of information. The elements in the blocks of information are then displayed, for example to a salesperson, as a function of these categories. In another embodiment, Document Object Modeling parsing is used to identify the structure of the web pages. In yet another embodiment, a support vector machine is used to categorize each block of information.

Abstract translation: 公开了一种网站挖掘工具，其从例如公司的网站中提取信息，并将所提取的信息呈现在图形用户界面（GUI）中。 在一个实施例中，来自网站的网页被存储在例如计算机存储器中，并且识别网页的结构。 然后根据该结构提取多个信息块，并将类别分配给每个信息块。 然后，作为这些类别的函数，将信息块中的元素显示为例如销售人员。 在另一个实施例中，文档对象建模解析用于识别网页的结构。 在另一个实施例中，支持向量机用于对每个信息块进行分类。

公开(公告)号：US20110137653A1

公开(公告)日：2011-06-09

申请号：US12631111

申请日：2009-12-04

Applicant: Andrej LJOLJE ,  Mazin Gilbert

Inventor： Andrej LJOLJE ,  Mazin Gilbert

IPC: G10L15/00

CPC classification number: G10L15/183 ,  G10L2015/227 ,  G10L2015/228

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for performing speech recognition based on a masked language model. A system configured to practice the method receives a masked language model including a plurality of words, wherein a bit mask identifies whether each of the plurality of words is allowed or disallowed with regard to an adaptation subset, receives input speech, generates a speech recognition lattice based on the received input speech using the masked language model, removes from the generated lattice words identified as disallowed by the bit mask for the adaptation subset, and recognizes the received speech based on the lattice. Alternatively during the generation step, the system can only add words indicated as allowed by the bit mask. The bit mask can be separate from or incorporated as part of the masked language model. The system can dynamically update the adaptation subset and bit mask.

Abstract translation: 本文公开了用于基于掩蔽语言模型执行语音识别的系统，方法和计算机可读存储介质。 被配置为实施该方法的系统接收包括多个单词的掩蔽语言模型，其中位掩码识别关于自适应子集是否允许或不允许多个单词中的每一个，接收输入语音，生成语音识别格 基于使用掩蔽语言模型的接收到的输入语音，从由适配子集的位掩码识别为不允许的生成的格子字中移除，并且基于格子识别接收的语音。 或者在生成步骤期间，系统只能添加由位掩码允许的指示的字。 位掩码可以与掩蔽语言模型的一部分分开或并入。 系统可以动态地更新自适应子集和位掩码。

公开(公告)号：US20110022379A1

公开(公告)日：2011-01-27

申请号：US12897149

申请日：2010-10-04

Applicant: Srinivas Bangalore ,  David Crawford Gibbon ,  Mazin Gilbert ,  Patrick Guy Haffner ,  Zhu Liu ,  Behzad Shahraray

Inventor： Srinivas Bangalore ,  David Crawford Gibbon ,  Mazin Gilbert ,  Patrick Guy Haffner ,  Zhu Liu ,  Behzad Shahraray

IPC: G06F17/28

CPC classification number: G06F17/289

Abstract: In an embodiment, a method of providing an on demand translation service is provided. A subscriber may be charged a reduced fee or no fee for use of the on demand translation service in exchange for displaying commercial messages to the subscriber, the commercial messages being selected based on subscriber information. A multimedia signal including information in a source language may be received. The information may be obtained as text in the source language from the multimedia signal. The text may be translated from the source language to a target language. Translated information, based on the translated text, may be transmitted to a processing device for presentation to the subscriber. The received multimedia signal may be sent to a multimedia device for viewing.

Abstract translation: 在一个实施例中，提供了提供按需翻译服务的方法。 用户可能被收取减少的费用或不使用按需翻译服务的费用，以便向用户显示商业消息，基于用户信息选​​择商业消息。 可以接收包括源语言的信息的多媒体信号。 可以从多媒体信号中获取源语言中的文本信息。 文本可以从源语言翻译成目标语言。 基于翻译的文本的翻译信息可以被发送到处理设备以呈现给订阅者。 所接收的多媒体信号可以被发送到多媒体设备以供观看。