专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20060224535A1 Action selection for reinforcement learning using influence diagrams 失效
标题翻译：使用影响图强化学习的行动选择
公开(公告)号：US20060224535A1
公开(公告)日：2006-10-05
申请号：US11169503
申请日：2005-06-29
申请人： David Chickering , Timothy Paek , Eric Horvitz
发明人： David Chickering , Timothy Paek , Eric Horvitz
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： A system and method for online reinforcement learning is provided. In particular, a method for performing the explore-vs.-exploit tradeoff is provided. Although the method is heuristic, it can be applied in a principled manner while simultaneously learning the parameters and/or structure of the model (e.g., Bayesian network model). The system includes a model which receives an input (e.g., from a user) and provides a probability distribution associated with uncertainty regarding parameters of the model to a decision engine. The decision engine can determine whether to exploit the information known to it or to explore to obtain additional information based, at least in part, upon the explore-vs.-exploit tradeoff (e.g., Thompson strategy). A reinforcement learning component can obtain additional information (e.g., feedback from a user) and update parameter(s) and/or the structure of the model. The system can be employed in scenarios in which an influence diagram is used to make repeated decisions and maximization of long-term expected utility is desired.
摘要翻译：提供了一种在线强化学习的系统和方法。特别地，提供了用于执行探索与利用的权衡的方法。尽管该方法是启发式的，但是它可以以原则的方式应用，同时学习模型的参数和/或结构（例如，贝叶斯网络模型）。该系统包括接收输入（例如，来自用户）并且向决策引擎提供与关于模型的参数的不确定性相关联的概率分布的模型。决策引擎可以确定是否利用已知的信息，或者至少部分地基于探索与利用权衡（Thompson策略）来探索获取附加信息。强化学习组件可以获得附加信息（例如，来自用户的反馈）和更新参数和/或模型的结构。该系统可用于使用影响图进行重复决策的场景，并期望实现长期预期效用的最大化。

2. 发明申请

US20060206337A1 Online learning for dialog systems 有权
标题翻译：在线学习对话系统
公开(公告)号：US20060206337A1
公开(公告)日：2006-09-14
申请号：US11170999
申请日：2005-06-29
申请人： Timothy Paek , David Chickering , Eric Horvitz
发明人： Timothy Paek , David Chickering , Eric Horvitz
IPC分类号： G10L21/00
CPC分类号： G10L15/065
摘要： An online dialog system and method are provided. The dialog system receives speech input and outputs an action according to its models. After executing the action, the system receives feedback from the environment or user. The system immediately utilizes the feedback to update its models in an online fashion.
摘要翻译：提供在线对话系统和方法。对话系统接收语音输入，并根据其模型输出动作。执行该操作后，系统会收到来自环境或用户的反馈。系统立即利用反馈以在线方式更新其模型。

3. 发明申请

US20060206333A1 Speaker-dependent dialog adaptation 审中-公开
标题翻译：与扬声器相关的对话框适应
公开(公告)号：US20060206333A1
公开(公告)日：2006-09-14
申请号：US11170998
申请日：2005-06-29
申请人： Timothy Paek , David Chickering , Eric Horvitz
发明人： Timothy Paek , David Chickering , Eric Horvitz
IPC分类号： G10L13/00
CPC分类号： G10L15/22 , G10L15/07
摘要： A simulation environment for adapting a speech model (e.g., baseline model) to a user is provided. The user can interact with a base parametric speech model (e.g., statistical model with learnable parameters such as a Bayesian network) and give positive and/or negative feedback when the dialog system has performed what the user considers to be appropriate and/or inappropriate action(s). From the user feedback, the dialog system learns to take actions customized for the particular user. Speaker-dependent adaptation can be extended to the dialog level by performing maximum likelihood linear regression (MLLR) adaptation simultaneously with dialog personalization. Users are immediately able to observe how their feedback has caused the dialog system to adapt, and can quit training whenever they feel that the dialog system has adapted enough for current purposes.
摘要翻译：提供了一种用于将语音模型（例如，基准模型）适配到用户的模拟环境。用户可以与基本参数语音模型（例如，具有诸如贝叶斯网络的可学习参数的统计模型）交互，并且当对话系统执行用户认为是适当的和/或不适当的动作时给出正和负反馈（s）。从用户反馈中，对话系统学习采取针对特定用户定制的动作。通过与对话个性化同时执行最大似然线性回归（MLLR）适应，可以将扬声器依赖的适应扩展到对话级。用户可以立即观察他们的反馈如何使对话系统适应，并且只要他们觉得对话系统已经足够适应当前的目的，就可以退出训练。

4. 发明申请

US20070239453A1 AUGMENTING CONTEXT-FREE GRAMMARS WITH BACK-OFF GRAMMARS FOR PROCESSING OUT-OF-GRAMMAR UTTERANCES 审中-公开
标题翻译：使用后处理灰度来处理超出灰度特征的无限自由的GRAMMARS
公开(公告)号：US20070239453A1
公开(公告)日：2007-10-11
申请号：US11278893
申请日：2006-04-06
申请人： Timothy Paek , David Chickering , Eric Badger , Qiang Wu
发明人： Timothy Paek , David Chickering , Eric Badger , Qiang Wu
IPC分类号： G10L15/18
CPC分类号： G10L15/065
摘要： Architecture for integrating and generating back-off grammars (BOG) in a speech recognition application for recognizing out-of-grammar (OOG) utterances and updating the context-free grammars (CFG) with the results. A parsing component identifies keywords and/or slots from user utterances and a grammar generation component adds filler tags before and/or after the keywords and slots to create new grammar rules. The BOG can be generated from these new grammar rules and can be used to process the OOG user utterances. By processing the OOG user utterances through the BOG, the architecture can recognize and perform the intended task on behalf of the user.
摘要翻译：用于在语音识别应用程序中集成和生成后退语法（BOG）的体系结构，用于识别语法（OOG）语音并更新无上下文语法（CFG）。解析组件识别来自用户话语的关键字和/或时隙，并且语法生成组件在关键词和时隙之前和之后添加填充标签以创建新的语法规则。 BOG可以从这些新的语法规则生成，并可用于处理OOG用户的话语。通过通过BOG处理OOG用户话语，架构可以代表用户识别并执行预期的任务。

5. 发明授权

US06490698B1 Multi-level decision-analytic approach to failure and repair in human-computer interactions 有权
标题翻译：多层次的决策分析方法在人机交互中失败和修复
公开(公告)号：US06490698B1
公开(公告)日：2002-12-03
申请号：US09326043
申请日：1999-06-04
申请人： Eric Horvitz , Timothy Paek
发明人： Eric Horvitz , Timothy Paek
IPC分类号： G06F1100
CPC分类号： G10L15/1822 , G06N7/005
摘要： A multi-level decision-analytic approach to failure and repair within computer-user communications is disclosed. In one embodiment, a computerized system for repairing communication failure within a computer-user interaction context includes a maintenance module, an intention module, and a conversation control subsystem. The maintenance module manages uncertainty regarding signal identification and channel fidelity. The intention module is supported by the maintenance module, and manages uncertainty about the recognition of user's goals from signals. The conversation control subsystem surrounds both the modules, and manages the joint activity between the computer and the user, and one or more high-level events regarding the joint activity.
摘要翻译：公开了一种用于计算机用户通信中的故障和修复的多层决策分析方法。在一个实施例中，用于修复计算机 - 用户交互环境内的通信故障的计算机化系统包括维护模块，意图模块和会话控制子系统。维护模块管理信号识别和信道保真度的不确定性。意图模块由维护模块支持，并且管理从信号识别用户目标的不确定性。会话控制子系统围绕两个模块，并管理计算机和用户之间的联合活动，以及关于联合活动的一个或多个高级事件。

6. 发明申请

US20070239454A1 PERSONALIZING A CONTEXT-FREE GRAMMAR USING A DICTATION LANGUAGE MODEL 有权
标题翻译：使用引用语言模型个性化无背景GRAMMAR
公开(公告)号：US20070239454A1
公开(公告)日：2007-10-11
申请号：US11278899
申请日：2006-04-06
申请人： Timothy Paek , David Chickering , Eric Badger , Qiang Wu
发明人： Timothy Paek , David Chickering , Eric Badger , Qiang Wu
IPC分类号： G10L15/18
CPC分类号： G10L15/19 , G10L2015/088
摘要： Architecture for integrating and generating back-off grammars (BOG) in a speech recognition application for recognizing out-of-grammar (OOG) utterances and updating the context-free grammars (CFG) with the results. A parsing component identifies keywords and/or slots from user utterances and a grammar generation component adds filler tags before and/or after the keywords and slots to create new grammar rules. The BOG can be generated from these new grammar rules and can be used to process the OOG user utterances. By processing the OOG user utterances through the BOG, the architecture can recognize and perform the intended task on behalf of the user.
摘要翻译：用于在语音识别应用程序中集成和生成后退语法（BOG）的体系结构，用于识别语法（OOG）语音并更新无上下文语法（CFG）。解析组件识别来自用户话语的关键字和/或时隙，并且语法生成组件在关键词和时隙之前和之后添加填充标签以创建新的语法规则。 BOG可以从这些新的语法规则生成，并可用于处理OOG用户的话语。通过通过BOG处理OOG用户话语，架构可以代表用户识别并执行预期的任务。

7. 发明申请

US20070239637A1 Using predictive user models for language modeling on a personal device 失效
标题翻译：在个人设备上使用预测用户模型进行语言建模
公开(公告)号：US20070239637A1
公开(公告)日：2007-10-11
申请号：US11378024
申请日：2006-03-17
申请人： Timothy Paek , David Chickering
发明人： Timothy Paek , David Chickering
IPC分类号： G06F15/18
CPC分类号： G06F17/276 , G06N99/005 , G10L15/183 , G10L15/22 , G10L2015/0631
摘要： A system and method for prediction of a user goal for command/control of a personal device (e.g., mobile phone) is provided. The system employs statistical model(s) that can predict a command based, at least in part, on past user behavior (e.g., probability distribution over a set of predicates, and, optionally arguments). Further, the system can be employed with a speech recognition component to facilitate language modeling for predicting the user goal. The system can include predictive user models (e.g., predicate model and argument model) that receive a user input (e.g., utterance) and employ statistical modeling to determine the likely command without regard to the actual content of the input (e.g., utterance). The system employs features for predicting the next user goal which can be stored in a user data store. Features can capture personal idiosyncrasies or systematic patterns of usage (e.g., device-related, time-related, predicate-related, contact-specific and/or periodic features).
摘要翻译：提供了一种用于预测用于个人设备（例如，移动电话）的命令/控制的用户目标的系统和方法。该系统使用至少部分地基于过去的用户行为（例如，一组谓词上的概率分布，以及可选的参数）来预测命令的统计模型。此外，该系统可以与语音识别组件一起使用以便于用于预测用户目标的语言建模。该系统可以包括接收用户输入（例如，话语）并且采用统计建模来确定可能的命令而不考虑输入的实际内容（例如，话语）的预测用户模型（例如谓词模型和参数模型）。该系统采用用于预测可存储在用户数据存储中的下一个用户目标的特征。特征可以捕获个人特征或系统的使用模式（例如，与设备相关的，与时间相关的，谓词相关的，特定于接触的和/或周期的特征）。

8. 发明申请

US20070233497A1 Dialog repair based on discrepancies between user model predictions and speech recognition results 有权
标题翻译：基于用户模型预测和语音识别结果之间的差异的对话框修复
公开(公告)号：US20070233497A1
公开(公告)日：2007-10-04
申请号：US11393321
申请日：2006-03-30
申请人： Timothy Paek , David Chickering
发明人： Timothy Paek , David Chickering
IPC分类号： G10L21/00
CPC分类号： G10L15/22 , G10L2015/228
摘要： An architecture is presented that leverages discrepancies between user model predictions and speech recognition results by identifying discrepancies between the predictive data and the speech recognition data and repairing the data based in part on the discrepancy. User model predictions predict what goal or action speech application users are likely to pursue based in part on past user behavior. Speech recognition results indicate what goal speech application users are likely to have spoken based in part on words spoken under specific constraints. Discrepancies between the predictive data and the speech recognition data are identified and a dialog repair is engaged for repairing these discrepancies. By engaging in repairs when there is a discrepancy between the predictive results and the speech recognition results, and utilizing feedback obtained via interaction with a user, the architecture can learn about the reliability of both user model predictions and speech recognition results for future processing.
摘要翻译：提出了一种通过识别预测数据和语音识别数据之间的差异以及部分地基于差异来修复数据来利用用户模型预测和语音识别结果之间的差异的架构。用户模型预测部分地基于过去的用户行为来预测用户可能追求的目标或动作语音应用程序。语音识别结果表明，目标语音应用程序用户可能部分地基于特定约束条件下所说的话语言。识别预测数据和语音识别数据之间的差异，并进行对话修复以修复这些差异。通过在预测结果和语音识别结果之间存在差异并利用通过与用户的交互获得的反馈来进行维修，架构可以了解用户模型预测和语音识别结果的可靠性以供将来处理。

9. 发明申请

US20070219974A1 Using generic predictive models for slot values in language modeling 有权
标题翻译：在语言建模中使用时隙值的通用预测模型
公开(公告)号：US20070219974A1
公开(公告)日：2007-09-20
申请号：US11378202
申请日：2006-03-17
申请人： David Chickering , Timothy Paek
发明人： David Chickering , Timothy Paek
IPC分类号： G06F17/30
CPC分类号： G06Q10/10
摘要： A generic predictive argument model that can be applied to a set of slot values to predict a target slot value is provided. The generic predictive argument model can predict whether or not a particular value or item is the intended target of the user command given various features. A prediction for each of the slot values can then be normalized to infer a distribution over all values or items. For any set of slot values (e.g., contacts), a number of binary variables are created that indicate whether or not each specific slot value was the intended target. For each slot value, a set of input features can be employed to predict the corresponding binary variable. These input features are generic properties of the contact that are “instantiated” based on properties of the contact (e.g., contact-specific features). These contact-specific features can be stored in a user data store.
摘要翻译：提供了可应用于一组时隙值以预测目标时隙值的通用预测参数模型。通用预测参数模型可以预测特定值或项目是否是给定各种特征的用户命令的预期目标。然后可以对每个时隙值的预测进行归一化以推断所有值或项目上的分布。对于任何一组时隙值（例如，联系人），创建多个二进制变量，指示每个特定时隙值是否为预期目标。对于每个时隙值，可以采用一组输入特征来预测相应的二进制变量。这些输入特征是基于联系人的属性（例如，联系人特定的特征）被“实例化”的联系人的通用属性。这些联系人特定的功能可以存储在用户数据存储中。

10. 发明申请

US20060206332A1 Easy generation and automatic training of spoken dialog systems using text-to-speech 有权
标题翻译：使用文字转语音轻松地生成和自动训练语音对话系统
公开(公告)号：US20060206332A1
公开(公告)日：2006-09-14
申请号：US11170584
申请日：2005-06-29
申请人： Timothy Paek , David Chickering
发明人： Timothy Paek , David Chickering
IPC分类号： G10L15/18
CPC分类号： G10L15/22 , G10L13/00 , G10L15/063
摘要： A dialog system training environment and method using text-to-speech (TTS) are provided. The only knowledge a designer requires is a simple specification of when the dialog system has failed or succeeded, and for any state of the dialog, a list of the possible actions the system can take. The training environment simulates a user using TTS varied at adjustable levels, a dialog action model of a dialog system responds to the produced utterance by trying out all possible actions until it has failed or succeeded. From the data accumulated in the training environment it is possible for the dialog action model to learn which states to go to when it observes the appropriate speech and dialog features so as to increase the likelihood of success. The data can also be used to improve the speech model.
摘要翻译：提供了使用文本到语音（TTS）的对话系统训练环境和方法。设计师需要的唯一知识是对话系统何时失败或成功的简单规范，对于对话框的任何状态，系统可能采取的行动的列表。训练环境模拟用户使用可调节级别变化的TTS，对话系统的对话动作模型通过尝试所有可能的动作直到失败或成功来响应所产生的话语。从训练环境中累积的数据可以看出，当对话动作模型观察适当的语音和对话特征时，对话动作模型可以了解哪些状态可以增加成功的可能性。数据也可用于改进语音模型。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式