公开(公告)号：US07720683B1

公开(公告)日：2010-05-18

申请号：US10866232

申请日：2004-06-10

Applicant: Pieter J. Vermeulen ,  Robert E. Savoie ,  Stephen Sutton ,  Forrest S. Mozer

Inventor： Pieter J. Vermeulen ,  Robert E. Savoie ,  Stephen Sutton ,  Forrest S. Mozer

IPC: G10L15/04

CPC classification number: G10L15/22 ,  G10L15/285 ,  G10L2015/0631

Abstract: A speech recognition technique is described that has the dual benefits of not requiring collection of recordings for training while using computational resources that are cost-compatible with consumer electronic products. Methods are described for improving the recognition accuracy of a recognizer by developer interaction with a design tool that iterates the recognition data during development of a recognition set of utterances and that allows controlling and minimizing the computational resources required to implement the recognizer in hardware.

Abstract translation: 描述了语音识别技术，其具有在使用与消费电子产品成本兼容的计算资源时不需要收集用于训练的记录的双重优点。 描述了用于通过开发人员与设计工具的交互来提高识别器的识别精度的方法，该设计工具在开发识别语音集合期间迭代识别数据，并且允许控制和最小化在硬件中实现识别器所需的计算资源。

公开(公告)号：US08781825B2

公开(公告)日：2014-07-15

申请号：US13217134

申请日：2011-08-24

Applicant: Jonathan Shaw ,  Pieter Vermeulen ,  Stephen Sutton ,  Robert Savoie

Inventor： Jonathan Shaw ,  Pieter Vermeulen ,  Stephen Sutton ,  Robert Savoie

IPC: G10L15/00 ,  G10L17/00 ,  G10L15/04 ,  G10L15/28

CPC classification number: G10L15/10 ,  G10L25/03

Abstract: Embodiments of the present invention improve methods of performing speech recognition. In one embodiment, the present invention includes a method comprising receiving a spoken utterance, processing the spoken utterance in a speech recognizer to generate a recognition result, determining consistencies of one or more parameters of component sounds of the spoken utterance, wherein the parameters are selected from the group consisting of duration, energy, and pitch, and wherein each component sound of the spoken utterance has a corresponding value of said parameter, and validating the recognition result based on the consistency of at least one of said parameters.

Abstract translation: 本发明的实施例改进了执行语音识别的方法。 在一个实施例中，本发明包括一种方法，包括接收口语话语，处理语音识别器中的语音话语以产生识别结果，确定所述语音话语的分量声音的一个或多个参数的一致性，其中选择参数 来自由持续时间，能量和音调组成的组，并且其中所述说话话语的每个分量声音具有所述参数的对应值，并且基于所述参数中的至少一个的一致性验证所述识别结果。

公开(公告)号：US20130054242A1

公开(公告)日：2013-02-28

申请号：US13217134

申请日：2011-08-24

Applicant: Jonathan Shaw ,  Pieter Vermeulen ,  Stephen Sutton ,  Robert Savoie

Inventor： Jonathan Shaw ,  Pieter Vermeulen ,  Stephen Sutton ,  Robert Savoie

IPC: G10L15/00

CPC classification number: G10L15/10 ,  G10L25/03

Abstract: Embodiments of the present invention improve methods of performing speech recognition. In one embodiment, the present invention includes a method comprising receiving a spoken utterance, processing the spoken utterance in a speech recognizer to generate a recognition result, determining consistencies of one or more parameters of component sounds of the spoken utterance, wherein the parameters are selected from the group consisting of duration, energy, and pitch, and wherein each component sound of the spoken utterance has a corresponding value of said parameter, and validating the recognition result based on the consistency of at least one of said parameters.

Abstract translation: 本发明的实施例改进了执行语音识别的方法。 在一个实施例中，本发明包括一种方法，包括接收口语话语，处理语音识别器中的语音话语以产生识别结果，确定所述语音话语的分量声音的一个或多个参数的一致性，其中选择参数 来自由持续时间，能量和音调组成的组，并且其中所述说话话语的每个分量声音具有所述参数的对应值，并且基于所述参数中的至少一个的一致性验证所述识别结果。

公开(公告)号：US20060169032A1

公开(公告)日：2006-08-03

申请号：US11399109

申请日：2006-04-06

Applicant: Stephen Sutton

Inventor： Stephen Sutton

IPC: G01N13/00

CPC classification number: G01N13/02 ,  G01N2013/0208

Abstract: Devices are presented which allow determination of unknown surface properties through the creation of a channel capillary, comprised in part of the subject surface or surfaces, and measurement of the capillary pressure created by a test fluid within the resultant channel. In various embodiments of the invention, a channel is created in a reference material which is bonded, through some mechanism, to the test surface in order to create a narrow capillary channel. In other embodiments of the invention, the capillary channel is created with test surfaces on either side of standoff strips which space the surfaces a precise distance from one another. Methods are presented for using these capillaries through immersion, along their length, in a bath of test fluid, such that the resultant fluid level provides a measure of capillary pressure. Being, in part, a consequence of the contact angle between the test fluid and the surface or surfaces under consideration, the capillary pressure is a convenient measure of surface properties inherently related to printability, affinity for adhesives, surface contamination by foreign substances, surface roughness, and the like. Devices are presented which allow measurement of test fluid height within the capillary, both in situations where a static equilibrium is achieved, and in situations where a dynamic contact angle is operative as the fluid rises or falls within the capillary.

Abstract translation: 提供了通过产生包含在受试者表面或部分表面中的通道毛细管以及由所得通道内的测试流体产生的毛细管压力的测量来确定未知表面性质的装置。 在本发明的各种实施例中，在参考材料中产生通道，该参考材料通过某种机构结合到测试表面上，以便产生窄的毛细通道。 在本发明的其它实施例中，毛细管通道产生在支座条的任一侧上的测试表面，这些测试表面使表面彼此间隔开精确的距离。 提出了使用这些毛细管的方法，沿着其长度在测试液体浴中浸入，使得所得到的液体水平提供了毛细管压力的量度。 部分原因是测试流体与所考虑的表面或表面之间的接触角的结果，毛细管压力是与印刷性固有相关的表面性质，对粘合剂的亲和性，外来物质的表面污染，表面粗糙度 ，等等。 给出了在实现静态平衡的情况下以及在流体升高或落入毛细管内时动态接触角可操作的情况下，允许在毛细管内测量测试流体高度的装置。

公开(公告)号：US20080232422A1

公开(公告)日：2008-09-25

申请号：US12089990

申请日：2006-11-02

Applicant: Stephen Sutton ,  Rodney Royston Watts

Inventor： Stephen Sutton ,  Rodney Royston Watts

IPC: H01S3/08

CPC classification number: G01N21/61 ,  G01N21/3504 ,  G01N21/39 ,  G01N2021/3513 ,  G01N2021/399 ,  G01N2201/0612 ,  H01S5/02296

Abstract: A transmitter unit is described for an open path gas detector. The unit comprises: an enclosure having a window; and a coherent radiation transmitter, e.g. a tuneable laser diode transmitter, located within the enclosure and configured to direct a beam of radiation through the window. The window is slanted with respect to the axis of the beam emitted by the transmitter such that no radiation from the transmitter that is directly incident on the window is reflected by the window directly onto the transmitter. Thereby interference fringes within the emitted radiation are reduced. Alternatively, the window may be replaced by a lens followed by an aperture such that the beam emitted by the transmitter is focused onto the aperture, thereby forming a beam of radiation passing out of the enclosure.

Abstract translation: 对于开放式气体检测器描述了发射器单元。 该单元包括：具有窗口的外壳; 和相干辐射发射器，例如。 可调谐的激光二极管发射器，位于外壳内并被配置成引导辐射束通过窗口。 窗口相对于由发射器发射的光束的轴线倾斜，使得来自直接入射在窗口上的发射器的辐射不被窗口直接反射到发射器上。 从而减少发射辐射内的干涉条纹。 或者，窗口可以由镜头代替，随后是孔，使得由发射器发射的光束被聚焦到孔上，从而形成辐射束通过外壳。

公开(公告)号：US06539354B1

公开(公告)日：2003-03-25

申请号：US09535100

申请日：2000-03-24

Applicant: Stephen Sutton ,  Pieter Vermeulen

Inventor： Stephen Sutton ,  Pieter Vermeulen

IPC: G10L1308

CPC classification number: G10L21/06 ,  G10L2021/105

Abstract: A method of producing synthetic visual speech according to this invention includes receiving an input containing speech information. One or more visemes that correspond to the speech input are then identified. Next, the weights of those visemes are calculated using a coarticulation engine including viseme deformability information. Finally, a synthetic visual speech output is produced based on the visemes' weights over time (or tracks). The synthetic visual speech output is combined with a synchronized audio output corresponding to the input to produce a multimedia output containing a 3D lipsyncing animation.

Abstract translation: 根据本发明的产生合成视觉语音的方法包括接收包含语音信息的输入。 然后识别与语音输入对应的一个或多个视力。 接下来，使用包括视力变形性信息的coarticulation引擎计算这些视力的权重。 最后，基于随着时间（或轨道）的视角权重，产生合成视觉语音输出。 合成视觉语音输出与对应于输入的同步音频输出组合，以产生包含3D吸引力动画的多媒体输出。

公开(公告)号：US20080070432A1

公开(公告)日：2008-03-20

申请号：US11948013

申请日：2007-11-30

Applicant: STEPHEN SUTTON

Inventor： STEPHEN SUTTON

IPC: H01R29/00

CPC classification number: H01R31/06 ,  B60R16/0207 ,  H01H1/5866 ,  H01H50/14 ,  H01R27/00

Abstract: The invented apparatus is designed for use within a vehicle's electrical system. The apparatus electrically couples a plug having a first electrical contact configuration with a relay having a different electrical contact configuration. The apparatus provides an easy and inexpensive solution for replacing relay's that have different electrical contact configurations.

Abstract translation: 本发明的设备被设计用于在车辆的电气系统内使用。 该装置将具有第一电接触构造的插头与具有不同电接触构造的继电器电耦合。 该设备为替代具有不同电接触配置的继电器提供了一种简单而便宜的解决方案。

公开(公告)号：US20060221558A1

公开(公告)日：2006-10-05

申请号：US11096977

申请日：2005-03-31

Applicant: Stephen Sutton

Inventor： Stephen Sutton

IPC: H02B1/00

CPC classification number: H01R31/06 ,  B60R16/0207 ,  H01H1/5866 ,  H01H50/14 ,  H01R27/00

Abstract: The invented apparatus is designed for use within a vehicle's electrical system. The apparatus electrically couples a plug having a first electrical contact configuration with a relay having a different electrical contact configuration. The apparatus provides an easy and inexpensive solution for replacing relay's that have different electrical contact configurations.

Abstract translation: 本发明的设备被设计用于在车辆的电气系统内使用。 该装置将具有第一电接触构造的插头与具有不同电接触构造的继电器电耦合。 该设备为替代具有不同电接触配置的继电器提供了一种简单而便宜的解决方案。