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

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。

2. 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。

3. 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。

4. 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。

5. 发明授权

US08345832B2 Enhanced voicemail usage through automatic voicemail preview 有权
标题翻译：通过自动语音信箱预览增强语音信箱的使用
公开(公告)号：US08345832B2
公开(公告)日：2013-01-01
申请号：US12351681
申请日：2009-01-09
申请人： Jon Hamaker , Keith Herold , Michael Wilson , David Notario , Tom Millet
发明人： Jon Hamaker , Keith Herold , Michael Wilson , David Notario , Tom Millet
IPC分类号： H04M1/64
CPC分类号： H04M1/271 , G06Q10/107 , H04M3/53358 , H04M2203/253 , H04M2203/4509
摘要： Textual preview of a voicemail is generated and provided through email or similar media to users along with the audio version. Transcription of the textual version, as well as additional capabilities such as actionable terms, playback-jump, switching between text and audio versions, direct or metadata based searchability, and enhanced response capabilities are provided based on contextual data obtained from voicemail metadata and user associated data stores such as contact list, email history.
摘要翻译：通过电子邮件或类似媒体生成并提供语音邮件的文本预览，以及音频版本。基于从语音邮件元数据和用户相关联获得的语境数据，提供文本版本的转录以及诸如可操作术语，回放跳转，文本和音频版本之间的切换，直接或基于元数据的可搜索性以及增强的响应能力等附加功能数据存储，如联系人列表，电子邮件历史记录。

6. 发明申请

US20080221896A1 Grammar confusability metric for speech recognition 有权
标题翻译：用于语音识别的语法混淆度量
公开(公告)号：US20080221896A1
公开(公告)日：2008-09-11
申请号：US11716210
申请日：2007-03-09
申请人： Oin Cai , Jon Hamaker
发明人： Oin Cai , Jon Hamaker
IPC分类号： G10L11/00
CPC分类号： G10L15/01 , G10L15/19
摘要： Architecture for testing an application grammar for the presence of confusable terms. A grammar confusability metric (GCM) is generated for describing a likelihood that a reference term will be confused by the speech recognizer with another term phrase currently allowed by active grammar rules. The GCM is used to flag processing of two phrases in the grammar that have different semantic meaning, but that the speech recognizer could have difficulty distinguishing reliably. A built-in acoustic model is analyzed and feature vectors generated that are close to the acoustic properties of the input term. The feature vectors are then sent for recognition. A statistically random sampling method is applied to explore the acoustic properties of feature vectors of the input term phrase spatially and temporally. The feature vectors are perturbed in the neighborhood of the time domain and the Gaussian mixture model to which the feature vectors belong.
摘要翻译：用于测试应用程序语法的架构，用于存在混淆的术语。生成语法混淆度量（GCM），用于描述参考术语将被语音识别器与当前被活动语法规则允许的另一术语短语混淆的可能性。 GCM用于标记具有不同语义含义的语法中的两个短语的处理，但语音识别器可能难以区分可靠。分析内置的声学模型，生成与输入项的声学特性接近的特征向量。然后发送特征向量进行识别。应用统计学随机抽样方法，在空间和时间上探索输入项短语的特征向量的声学特性。特征向量在时域附近被扰乱，特征向量属于该高斯混合模型。

7. 发明申请

US20100177877A1 ENHANCED VOICEMAIL USAGE THROUGH AUTOMATIC VOICEMAIL PREVIEW 有权
标题翻译：通过自动VOICEMAIL预览来增强语音信箱的使用
公开(公告)号：US20100177877A1
公开(公告)日：2010-07-15
申请号：US12351681
申请日：2009-01-09
申请人： Jon Hamaker , Keith Herold , Michael Wilson , David Notario , Tom Millett
发明人： Jon Hamaker , Keith Herold , Michael Wilson , David Notario , Tom Millett
IPC分类号： H04M11/00 , G10L15/26
CPC分类号： H04M1/271 , G06Q10/107 , H04M3/53358 , H04M2203/253 , H04M2203/4509
摘要： Textual preview of a voicemail is generated and provided through email or similar media to users along with the audio version. Transcription of the textual version, as well as additional capabilities such as actionable terms, playback-jump, switching between text and audio versions, direct or metadata based searchability, and enhanced response capabilities are provided based on contextual data obtained from voicemail metadata and user associated data stores such as contact list, email history.
摘要翻译：通过电子邮件或类似媒体生成并提供语音邮件的文本预览，以及音频版本。基于从语音邮件元数据和用户相关联获得的语境数据，提供文本版本的转录以及诸如可操作术语，回放跳转，文本和音频版本之间的切换，直接或基于元数据的可搜索性以及增强的响应能力等附加功能数据存储，如联系人列表，电子邮件历史记录。

8. 发明授权

US5090712A Non-contacting, gap-type seal having a ring with a patterned microdam seal face 失效
标题翻译：非接触式，带有图案的MICRODAM密封面的GAP型密封
公开(公告)号：US5090712A
公开(公告)日：1992-02-25
申请号：US553397
申请日：1990-07-17
申请人： Glenn G. Pecht , Jon Hamaker
发明人： Glenn G. Pecht , Jon Hamaker
IPC分类号： F16J15/34
CPC分类号： F16J15/3412
摘要： A seal face of a ring used in a non-contacting, gap-type seal having an annular groove area with microdams, each having a preferable width of about 0.025 inches, between a plurality of groove surface areas. The microdams provide a boundary to the groove surface areas whereby the recess of each groove surface area bounded by the microdams acts as a unitary pressure zone and the pressure in the separate zones decreases in a series of steps as measured from one circumference of the ring to the other circumference.

9. 发明授权

US5492341A Non-contacting, gap-type seal having a ring with a patterned seal face 失效
标题翻译：具有带图案化密封面的环的非接触的间隙型密封
公开(公告)号：US5492341A
公开(公告)日：1996-02-20
申请号：US83614
申请日：1993-06-28
申请人： Glenn G. Pecht , Jon Hamaker , Peter L. Kay
发明人： Glenn G. Pecht , Jon Hamaker , Peter L. Kay
IPC分类号： F16J15/34
CPC分类号： F16J15/3412
摘要： A seal face of at least one ring used in a non-contacting, gap-type mechanical end face seal having a pattern including an optional dam and an annular grooved area. The annular grooved area has one of several embodiments, including entrance lands which are essentially triangular and have one side contiguous with one circumferential edge of the annular grooved area. These embodiments further include a set of converging boundary sides of the groove to provide a pressure zone effect. Seal face patterns include a contiguous groove around the circumference of the seal face and a series of annular bands comprising a repeating pattern of an essentially triangular groove interposed between two adjacent, but oppositely oriented, lands. One seal face pattern includes a circular or elliptical groove being open to the circumferential edge, thus providing an entrance land effect, and which includes a circular or elliptical land within it so that the boundaries between the lands and groove converge to provide the pressure zone effect.
摘要翻译：至少一个环的密封面用于非接触间隙型机械端面密封件，其具有包括可选的坝和环形槽区域的图案。环形沟槽区域具有几个实施例中的一个，包括基本上为三角形并且具有与环形开槽区域的一个圆周边缘相邻的一侧的入口平台。这些实施例还包括凹槽的一组会聚的边界侧以提供压力区效应。密封面图案包括围绕密封面的周边的连续凹槽和一系列环形带，其包括插入在两个相邻但相对定向的平台之间的基本上三角形凹槽的重复图案。一个密封面图案包括对圆周边缘开口的圆形或椭圆形凹槽，从而提供入口平台效应，并且在其内包括圆形或椭圆形的平台，使得凸台和凹槽之间的边界会聚以提供压力区域效应。

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