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. 发明授权

US08386251B2 Progressive application of knowledge sources in multistage speech recognition 有权
标题翻译：知识来源在多级语音识别中的逐步应用
公开(公告)号：US08386251B2
公开(公告)日：2013-02-26
申请号：US12479986
申请日：2009-06-08
申请人： Nikko Strom , Julian Odell , Jon Hamaker
发明人： Nikko Strom , Julian Odell , Jon Hamaker
IPC分类号： G10L17/00
CPC分类号： G10L15/08 , G10L15/065 , G10L15/32
摘要： A speech recognition system is provided with iteratively refined multiple passes through the received data to enhance the accuracy of the results by introducing constraints and adaptation from initial passes into subsequent recognition operations. The multiple passes are performed on an initial utterance received from a user. The iteratively enhanced subsequent passes are also performed on following utterances received from the user increasing an overall system efficiency and accuracy.
摘要翻译：提供语音识别系统，其经过接收的数据进行迭代精确的多次通过，通过引入约束和从初始传递到随后的识别操作的调整来提高结果的准确性。在从用户接收到的初始话语中执行多遍。对从用户接收的以下话语也执行迭代增强的后续遍历，从而提高整个系统的效率和精度。

2. 发明授权

US09111540B2 Local and remote aggregation of feedback data for speech recognition 有权
标题翻译：用于语音识别的反馈数据的本地和远程聚合
公开(公告)号：US09111540B2
公开(公告)日：2015-08-18
申请号：US12481439
申请日：2009-06-09
申请人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
发明人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
IPC分类号： G10L15/00 , G10L15/065 , G10L15/30 , G10L15/06
CPC分类号： G10L15/01 , G10L15/02 , G10L15/063 , G10L15/065 , G10L15/14 , G10L15/187 , G10L15/30 , G10L2015/025 , G10L2015/0631 , G10L2015/0635
摘要： A local feedback mechanism for customizing training models based on user data and directed user feedback is provided in speech recognition applications. The feedback data is filtered at different levels to address privacy concerns for local storage and for submittal to a system developer for enhancement of generic training models.
摘要翻译：在语音识别应用中提供了基于用户数据和定向用户反馈定制训练模型的本地反馈机制。反馈数据在不同级别进行过滤，以解决本地存储的隐私问题，并提交给系统开发人员以增强通用培训模型。

3. 发明申请

US20100312557A1 PROGRESSIVE APPLICATION OF KNOWLEDGE SOURCES IN MULTISTAGE SPEECH RECOGNITION 有权
标题翻译：知识来源在多语音识别中的积极应用
公开(公告)号：US20100312557A1
公开(公告)日：2010-12-09
申请号：US12479986
申请日：2009-06-08
申请人： Nikko Strom , Julian Odell , Jon Hamaker
发明人： Nikko Strom , Julian Odell , Jon Hamaker
IPC分类号： G10L15/00
CPC分类号： G10L15/08 , G10L15/065 , G10L15/32
摘要： A speech recognition system is provided with iteratively refined multiple passes through the received data to enhance the accuracy of the results by introducing constraints and adaptation from initial passes into subsequent recognition operations. The multiple passes are performed on an initial utterance received from a user. The iteratively enhanced subsequent passes are also performed on following utterances received from the user increasing an overall system efficiency and accuracy.
摘要翻译：提供语音识别系统，其经过接收的数据进行迭代精确的多次通过，通过引入约束和从初始传递到随后的识别操作的调整来提高结果的准确性。在从用户接收到的初始话语中执行多遍。对从用户接收的以下话语也执行迭代增强的后续遍历，从而提高整个系统的效率和精度。

4. 发明申请

US20100312555A1 LOCAL AND REMOTE AGGREGATION OF FEEDBACK DATA FOR SPEECH RECOGNITION 有权
标题翻译：用于语音识别的反馈数据的本地和远程聚合
公开(公告)号：US20100312555A1
公开(公告)日：2010-12-09
申请号：US12481439
申请日：2009-06-09
申请人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
发明人： Michael D. Plumpe , Julian Odell , Jon Hamaker , Rob Chambers , Christopher Le , Onur Domanic
IPC分类号： G10L15/00 , G10L15/04
CPC分类号： G10L15/01 , G10L15/02 , G10L15/063 , G10L15/065 , G10L15/14 , G10L15/187 , G10L15/30 , G10L2015/025 , G10L2015/0631 , G10L2015/0635
摘要： A local feedback mechanism for customizing training models based on user data and directed user feedback is provided in speech recognition applications. The feedback data is filtered at different levels to address privacy concerns for local storage and for submittal to a system developer for enhancement of generic training models.
摘要翻译：在语音识别应用中提供了基于用户数据和定向用户反馈定制训练模型的本地反馈机制。反馈数据在不同级别进行过滤，以解决本地存储的隐私问题，并提交给系统开发人员以增强通用培训模型。

5. 发明申请

US20070239458A1 Automatic identification of timing problems from speech data 有权
标题翻译：从语音数据自动识别时序问题
公开(公告)号：US20070239458A1
公开(公告)日：2007-10-11
申请号：US11392339
申请日：2006-03-29
申请人： Julian Odell , Stephen Potter
发明人： Julian Odell , Stephen Potter
IPC分类号： G10L21/00
CPC分类号： G10L15/26
摘要： A speech application is analyzed to automatically identify timing problems therein. Information related to the application is recorded and problems are identified. A recognizer can be utilized to perform recognition on the recorded information.
摘要翻译：分析语音应用程序以自动识别其中的定时问题。记录与应用有关的信息，并确定问题。可以利用识别器来对所记录的信息进行识别。

6. 发明申请

US20060178869A1 Classification filter for processing data for creating a language model 有权
标题翻译：用于处理用于创建语言模型的数据的分类过滤器
公开(公告)号：US20060178869A1
公开(公告)日：2006-08-10
申请号：US11054819
申请日：2005-02-10
申请人： Alejandro Acero , Dong Yu , Julian Odell , Milind Mahajan , Peter Mau
发明人： Alejandro Acero , Dong Yu , Julian Odell , Milind Mahajan , Peter Mau
IPC分类号： G06F17/21
CPC分类号： G06F17/2715 , G06F17/277 , G10L15/063 , G10L15/18 , G10L15/183
摘要： The method and apparatus utilize a filter to remove a variety of non-dictated words from data based on probability and improve the effectiveness of creating a language model.
摘要翻译：该方法和装置利用滤波器基于概率从数据中去除各种非指令词，并提高创建语言模型的有效性。

7. 发明申请

US20060184365A1 Word-specific acoustic models in a speech recognition system 失效
公开(公告)号：US20060184365A1
公开(公告)日：2006-08-17
申请号：US11403680
申请日：2006-04-13
申请人： Julian Odell , Shahid Durrani
发明人： Julian Odell , Shahid Durrani
IPC分类号： G10L15/26
CPC分类号： G10L15/063 , G10L15/187 , G10L2015/025 , G10L2015/0631
摘要： An acoustic model includes word-specific models, that are specific to candidate words. The candidate words would otherwise be mapped to a series of general phones. A sub-series of the general phones representing the candidate word is modeled by a new phone and the new phone is dedicated to the candidate word, or a small group of similar words, but the new phone is not shared among all words that otherwise map to the sub-series of general phones.

8. 发明授权

US06370505B1 Speech recognition system and method 失效
标题翻译：语音识别系统和方法
公开(公告)号：US06370505B1
公开(公告)日：2002-04-09
申请号：US09302370
申请日：1999-04-30
申请人： Julian Odell
发明人： Julian Odell
IPC分类号： G10L1514
CPC分类号： G10L15/144 , G10L15/10
摘要： The present invention relates to a method of processing speech, in which input speech is processed to determine an input speech vector (or) representing a sample of the speech. A number of possible output states are defined with each output state (j) being represented by a number of state mixture components (m). Each state mixture component is then approximated by a weighted sum of a number of predetermined generic components (x), allowing the likelihoods of each output states (j) corresponding to the input speech vector (or) to be determined.
摘要翻译：本发明涉及一种处理语音的方法，其中处理输入语音以确定表示语音样本的输入语音向量（或）。定义了多个可能的输出状态，每个输出状态（j）由多个状态混合分量（m）表示。每个状态混合分量然后通过预定的通用分量（x）的数量的加权和近似，从而允许确定与输入语音向量（或）相对应的每个输出状态（j）的似然性。

9. 发明申请

US20060293886A1 Confidence threshold tuning 有权
公开(公告)号：US20060293886A1
公开(公告)日：2006-12-28
申请号：US11168278
申请日：2005-06-28
申请人： Julian Odell , Li Jiang , Wei Zhang , Xiaodong He
发明人： Julian Odell , Li Jiang , Wei Zhang , Xiaodong He
IPC分类号： G10L15/00
CPC分类号： G10L15/08
摘要： An expected dialog-turn (ED) value is estimated for evaluating a speech application. Parameters such as a confidence threshold setting can be adjusted based on the expected dialog-turn value. In a particular example, recognition results and corresponding confidence scores are used to estimate the expected dialog-turn value. The recognition results can be associated with a possible outcome for the speech application and a cost for the possible outcome can be used to estimate the expected dialog-turn value.

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