公开(公告)号：US06701296B1

公开(公告)日：2004-03-02

申请号：US09472659

申请日：1999-12-27

Applicant: James F. Kramer ,  William R. George ,  Peter Lindener

Inventor： James F. Kramer ,  William R. George ,  Peter Lindener

IPC: G10L1524

CPC classification number: G06F3/016 ,  A61B5/1071 ,  A61B5/6806 ,  A61B5/7267 ,  A61B2562/0261 ,  G06F1/163 ,  G06F3/011 ,  G06F3/014 ,  G09B21/009 ,  G09B21/04

Abstract: Goniometers are provided having internal compensation employing two opposing variable resistance strain sensing elements separated by a flexible film. The goniometers may be used in sets for detecting complex hinge or joint movements, where patterns of hinge or joint positions may be used to define symbols. Algorithms are provided for parsing values from a system of goniometers in motion having information content.

Abstract translation: 提供测角器，其具有使用由柔性膜分离的两个相对的可变电阻应变传感元件的内部补偿。 测角仪可用于检测复合铰链或关节运动的组合，其中铰链或关节位置的图案可用于限定符号。 提供算法用于从具有信息内容的运动测角仪系统中解析值。

公开(公告)号：US06343269B1

公开(公告)日：2002-01-29

申请号：US09320708

申请日：1999-05-27

Applicant: Masaaki Harada ,  Shin Takeuchi

Inventor： Masaaki Harada ,  Shin Takeuchi

IPC: G10L1524

CPC classification number: G10L15/24 ,  G10L25/78

Abstract: An articulator shape input section detects movements of an articulator and generates feature data of speech. On the other hand, a speech mode detection section of a speech mode input section detects a mode of the speech. The kind of standard pattern is selected in accordance with the detected speech mode or a speech mode that is specified manually through a speech mode manual input section. A comparison section detects the speech by comparing the selected kind of standard pattern and the input feature data.

Abstract translation: 咬合器形状输入部分检测咬合器的移动并产生语音的特征数据。 另一方面，语音模式输入部分的语音模式检测部分检测语音的模式。 根据检测到的语音模式或通过语音模式手动输入部手动指定的语音模式来选择标准模式的种类。 比较部分通过比较所选择的标准模式和输入特征数据来检测语音。

公开(公告)号：US06820056B1

公开(公告)日：2004-11-16

申请号：US09717819

申请日：2000-11-21

Applicant: Shlomi Harif

Inventor： Shlomi Harif

IPC: G10L1524

CPC classification number: G10L15/26

Abstract: Simplifying command recognition from speech term recognition in speech recognition technology. A system for recognizing non-verbal sound commands within an interactive computer controlled display system with speech word recognition comprises standard technology for recognizing speech words in combination with a set up for storing a plurality of non-verbal sounds, each sound representative of a command. There are display means responsive to the recognizing of speech words for then displaying the recognized words. In response to the input of non-verbal sounds, there is a comparison of the input non-verbal sounds to said stored command sounds, together with means responsive to the comparing means for carrying out the command represented by a stored sound which compares to an input non-verbal sound. The non-verbal sounds may be voice generated or they may be otherwise physically generated. The commands may direct movement of data, e.g. cursors displayed on said display system. In such a case, an implementation is provided for inputting a sequential list of the sounds representative of said command directing movement to thereby produce a sequential movement of the displayed data, e.g. cursor movement.

Abstract translation: 在语音识别技术中简化语音词识别的命令识别。 用于在具有语音字识别的交互式计算机控制显示系统中识别非语言声音命令的系统包括用于识别语音单词的标准技术，与用于存储多个非语言声音的设置相结合，每个声音代表命令。 存在响应于识别语音单词然后显示所识别的单词的显示装置。 响应于非语言声音的输入，存在与所存储的命令声音的输入非语言声音的比较，以及响应于比较装置执行由存储的声音表示的命令的装置，该命令与 输入非语言声音。 非语言声音可能是语音产生的，或者可能以其他方式物理地产生。 这些命令可以引导数据的移动，例如 显示在所述显示系统上的光标。 在这种情况下，提供了用于输入表示所述命令指令运动的声音的顺序列表的实现，从而产生所显示的数据的顺序移动，例如， 光标移动。

公开(公告)号：US06185529B2

公开(公告)日：2001-02-06

申请号：US09153219

申请日：1998-09-14

Applicant: Chengjun Julian Chen ,  Frederick Yung-Fung Wu ,  James T. Yeh

Inventor： Chengjun Julian Chen ,  Frederick Yung-Fung Wu ,  James T. Yeh

IPC: G10L1524

CPC classification number: G10L15/25

Abstract: An apparatus and a method for imaging the mouth area laterally to produce reliable measurements of mouth and lip shapes for use in assisting the speech recognition task. A video camera is arranged with a headset and a microphone to capture a lateral profile image of a speaker. The lateral profile image is then used to compute features such as lip separation, lip shape and intrusion depth parameters. The parameters are used in real time, during speech recognition process to characterize and discriminate spoken phonemes to produce a high degree of accuracy in automatic speech recognition processing, especially in a noisy environment.

Abstract translation: 一种用于横向成像口腔的装置和方法，以产生用于辅助语音识别任务的口和嘴唇形状的可靠测量。 摄像机布置有耳机和麦克风以捕获扬声器的侧面轮廓图像。 然后使用侧面轮廓图像来计算诸如唇部分离，唇形和侵入深度参数的特征。 这些参数在语音识别过程中被实时地使用，以表征和辨别语音音素，以在自动语音识别处理中产生高度准确性，特别是在嘈杂的环境中。