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

US20100057464A1 SYSTEM AND METHOD FOR VARIABLE TEXT-TO-SPEECH WITH MINIMIZED DISTRACTION TO OPERATOR OF AN AUTOMOTIVE VEHICLE 失效
标题翻译：对汽车操作员进行最小化分类的可变文本语音的系统和方法
公开(公告)号：US20100057464A1
公开(公告)日：2010-03-04
申请号：US12202034
申请日：2008-08-29
申请人： DAVID MICHAEL KIRSCH , Ritchie Winson Huang
发明人： DAVID MICHAEL KIRSCH , Ritchie Winson Huang
IPC分类号： G10L13/08
CPC分类号： G10L13/033 , B60R16/0373 , G01C21/3629
摘要： A text-to-speech (TTS) system implemented in an automotive vehicle is dynamically tuned to increase intelligibility over a wide variety of vehicle operating states and environmental conditions by tuning characteristics of the synthesized voice in response to measured operating states. To decrease distractions to an operator of the vehicle, an embodiment of the invention prevents updates to the synthesized voice character from taking effect while a message phrase is being played. Instead, voice characteristics are updated only during natural phrase breaks. In another embodiment of the invention, a damping filter is applied to calculated changes in voice characteristics to prevent excessively rapid changes from being applied, reducing the likelihood of distracting the vehicle operator. In another embodiment of the invention, both phrase-break detectors and damping filters are employed.
摘要翻译：动态地调整在汽车中实现的文本到语音（TTS）系统，通过响应于测量的操作状态调谐合成语音的特性，通过调整各种车辆操作状态和环境条件来提高可懂度。为了减轻对车辆操作者的干扰，本发明的实施例防止在播放消息短语时合成语音角色的更新生效。相反，语音特征仅在自然短语中断时更新。在本发明的另一个实施例中，阻尼滤波器被应用于计算出的声音特性的变化，以防止施加过快的变化，从而减少分散车辆驾驶员的可能性。在本发明的另一个实施例中，采用短语中断检测器和阻尼滤波器。

2. 发明授权

US07831431B2 Voice recognition updates via remote broadcast signal 有权
标题翻译：通过远程广播信号更新语音识别
公开(公告)号：US07831431B2
公开(公告)日：2010-11-09
申请号：US11554830
申请日：2006-10-31
申请人： Ritchie Winson Huang , David Michael Kirsch
发明人： Ritchie Winson Huang , David Michael Kirsch
IPC分类号： G10L21/00
CPC分类号： G10L15/28 , G10L15/30
摘要： A method and a system are provided for dynamically updating voice recognition commands available for controlling a device in a vehicle. A receiver unit of a voice recognition system, located in the vehicle, receives a remotely transmitted broadcast signal. A processor of the voice recognition system extracts voice recognition data from a remaining portion of the broadcast signal and updates voice recognition commands stored in a memory unit, coupled to the processor, with the extracted voice recognition data. A voice input device of the voice recognition system receives a spoken command from a user. A voice recognition engine, coupled to the voice input device and the memory unit, determines whether the spoken command matches one of the stored voice recognition commands in the memory unit. If a match occurs, a recognized voice command is generated. The recognized voice command is sent to an affected device in the vehicle.
摘要翻译：提供了一种用于动态地更新可用于控制车辆中的设备的语音识别命令的方法和系统。位于车辆中的语音识别系统的接收机单元接收远程发送的广播信号。语音识别系统的处理器从广播信号的剩余部分中提取语音识别数据，并且利用所提取的语音识别数据来更新存储在耦合到处理器的存储器单元中的语音识别命令。语音识别系统的语音输入装置从用户接收口语命令。耦合到语音输入设备和存储器单元的语音识别引擎确定口语命令是否匹配存储器单元中存储的语音识别命令之一。如果发生匹配，则生成识别的语音命令。识别的语音命令被发送到车辆中的受影响的设备。

3. 发明申请

US20100057465A1 VARIABLE TEXT-TO-SPEECH FOR AUTOMOTIVE APPLICATION 审中-公开
标题翻译：用于汽车应用的可变文本语音
公开(公告)号：US20100057465A1
公开(公告)日：2010-03-04
申请号：US12203856
申请日：2008-09-03
申请人： DAVID MICHAEL KIRSCH , Ritchie Winson Huang
发明人： DAVID MICHAEL KIRSCH , Ritchie Winson Huang
IPC分类号： G10L13/08 , G10L21/00
CPC分类号： G10L13/033 , G01C21/3629
摘要： A text-to-speech (TTS) system implemented in an automotive vehicle is dynamically tuned to improve intelligibility over a wide variety of vehicle operating states and environmental conditions. In one embodiment of the present invention, a TTS system is interfaced to one or more vehicle sensors to measure parameters including vehicle speed, interior noise, visibility conditions, and road roughness, among others. In response to measurements of these operating parameters, TTS voice volume, pitch, and speed, among other parameters, may be tuned in order to improve intelligibility of the TTS voice system and increase its effectiveness for the operator of the vehicle.
摘要翻译：动态调整在汽车中实现的文本到语音（TTS）系统，以提高各种车辆运行状态和环境条件下的清晰度。在本发明的一个实施例中，TTS系统与一个或多个车辆传感器接口以测量包括车辆速度，内部噪声，可见度条件和道路粗糙度等参数。响应于这些操作参数的测量，可以调整TTS语音音量，音调和速度以及其他参数，以便提高TTS语音系统的可懂度并增加其对车辆操作者的有效性。

4. 发明申请

US20080103779A1 VOICE RECOGNITION UPDATES VIA REMOTE BROADCAST SIGNAL 有权
标题翻译：通过远程广播信号进行语音识别更新
公开(公告)号：US20080103779A1
公开(公告)日：2008-05-01
申请号：US11554830
申请日：2006-10-31
申请人： Ritchie Winson Huang , David Michael Kirsch
发明人： Ritchie Winson Huang , David Michael Kirsch
IPC分类号： G10L21/00
CPC分类号： G10L15/28 , G10L15/30
摘要： A method is provided for remotely and dynamically updating voice recognition commands available for controlling a device in a vehicle comprising the steps of: (a) receiving a broadcast signal comprising voice recognition data; (b) filtering the received broadcast signal by separating the voice recognition data from a remainder of the broadcast signal; (c) updating the a database containing previously stored voice recognition data with the received voice recognition data; (d) receiving a spoken command from an input device; (e) determining whether the received spoken command matches the voice recognition data stored in the database; and (f) generating a recognized voice command based at least in part on matching the received spoken command with the voice recognition data stored in the database.
摘要翻译：提供了一种用于远程和动态地更新可用于控制车辆中的设备的语音识别命令的方法，包括以下步骤：（a）接收包括语音识别数据的广播信号; （b）通过将语音识别数据与广播信号的剩余部分分离来对所接收的广播信号进行滤波; （c）用所接收的语音识别数据更新包含先前存储的语音识别数据的数据库; （d）从输入装置接收口语命令; （e）确定所接收的语音命令是否与存储在数据库中的语音识别数据相匹配; 以及（f）至少部分地基于将所接收的口语命令与存储在数据库中的语音识别数据进行匹配来生成识别的语音命令。

5. 发明授权

US08165881B2 System and method for variable text-to-speech with minimized distraction to operator of an automotive vehicle 失效
标题翻译：用于可变文本到语音的系统和方法，使机动车辆的操作者最小化分心
公开(公告)号：US08165881B2
公开(公告)日：2012-04-24
申请号：US12202034
申请日：2008-08-29
申请人： David Michael Kirsch , Ritchie Winson Huang
发明人： David Michael Kirsch , Ritchie Winson Huang
IPC分类号： G10L13/00 , G10L11/00
CPC分类号： G10L13/033 , B60R16/0373 , G01C21/3629
摘要： A text-to-speech (TTS) system implemented in an automotive vehicle is dynamically tuned to increase intelligibility over a wide variety of vehicle operating states and environmental conditions by tuning characteristics of the synthesized voice in response to measured operating states. To decrease distractions to an operator of the vehicle, an embodiment of the invention prevents updates to the synthesized voice character from taking effect while a message phrase is being played. Instead, voice characteristics are updated only during natural phrase breaks. In another embodiment of the invention, a damping filter is applied to calculated changes in voice characteristics to prevent excessively rapid changes from being applied, reducing the likelihood of distracting the vehicle operator. In another embodiment of the invention, both phrase-break detectors and damping filters are employed.
摘要翻译：动态地调整在汽车中实现的文本到语音（TTS）系统，通过响应于测量的操作状态调谐合成语音的特性，通过调整各种车辆操作状态和环境条件来提高可懂度。为了减轻对车辆操作者的干扰，本发明的实施例防止在播放消息短语时合成语音角色的更新生效。相反，语音特征仅在自然短语中断时更新。在本发明的另一个实施例中，阻尼滤波器被应用于计算出的声音特性的变化，以防止施加过快的变化，从而减少分散车辆驾驶员的可能性。在本发明的另一个实施例中，采用短语中断检测器和阻尼滤波器。

6. 发明申请

US20090083035A1 TEXT PRE-PROCESSING FOR TEXT-TO-SPEECH GENERATION 审中-公开
标题翻译：用于文本到语音生成的文本预处理
公开(公告)号：US20090083035A1
公开(公告)日：2009-03-26
申请号：US11861247
申请日：2007-09-25
申请人： Ritchie Winson Huang , David Michael Kirsch
发明人： Ritchie Winson Huang , David Michael Kirsch
IPC分类号： G10L13/00
CPC分类号： G10L13/08
摘要： A system and method are provided for improved speech synthesis, wherein text data is pre-processed according to updated grammar rules or a selected group of grammar rules. In one embodiment, the TTS system comprises a first memory adapted to store a text information database, a second memory adapted to store grammar rules, and a receiver adapted to receive update data regarding the grammar rules. The system also includes a TTS engine adapted to retrieve at least one text entry from the text information database, pre-process the at least one text entry by applying the updated grammar rules to the at least one text entry, and generate speech based at least in part on the least one pre-processed text entry.
摘要翻译：提供了一种用于改进语音合成的系统和方法，其中文本数据根据更新的语法规则或选定的语法规则组进行预处理。在一个实施例中，TTS系统包括适于存储文本信息数据库的第一存储器，适于存储语法规则的第二存储器，以及适于接收关于语法规则的更新数据的接收器。该系统还包括适于从文本信息数据库检索至少一个文本条目的TTS引擎，通过将更新的语法规则应用于至少一个文本条目来预处理该至少一个文本条目，并至少基于部分地在至少一个预处理的文本条目上。

7. 发明授权

US08781171B2 Object recognition in low-lux and high-lux conditions 有权
标题翻译：低勒克斯和高勒克斯条件下的物体识别
公开(公告)号：US08781171B2
公开(公告)日：2014-07-15
申请号：US13659826
申请日：2012-10-24
申请人： Josh Tyler King , Tarek El Dokor , Pedram Vaghefinazari , Stuart Masakazu Yamamoto , Ritchie Winson Huang
发明人： Josh Tyler King , Tarek El Dokor , Pedram Vaghefinazari , Stuart Masakazu Yamamoto , Ritchie Winson Huang
IPC分类号： G06K9/00
CPC分类号： G06K9/00335 , B60R1/00 , B60R2300/105 , B60R2300/106 , B60R2300/8006 , G06F3/017 , G06K9/00355 , G06K9/00832 , G06K9/00845 , G06K9/209 , H04N5/232 , H04N5/2351 , H04N5/33
摘要： A system for capturing image data for gestures from a passenger or a driver in a vehicle with a dynamic illumination level comprises a low-lux sensor equipped to capture image data in an environment with an illumination level below an illumination threshold, a high-lux sensor equipped to capture image data in the environment with the illumination level above the illumination threshold, and an object recognition module for activating the sensors. The object recognition module determines the illumination level of the environment and activates the low-lux sensor if the illumination level is below the illumination threshold. If the illumination level is above the threshold, the object recognition module activates the high-lux sensor.
摘要翻译：用于捕获来自具有动态照明级别的车辆中的乘客或驾驶员的手势的图像数据的系统包括：低勒克司传感器，其被配置为在具有低于照明阈值的照度水平的环境中拍摄图像数据;高勒克司传感器用于在照明级别高于照明阈值的环境中拍摄图像数据，以及用于激活传感器的对象识别模块。物体识别模块确定环境的照明水平，并且如果照明水平低于照明阈值，则激活低勒克司传感器。如果照明水平高于阈值，则物体识别模块激活高勒克斯传感器。

8. 发明申请

US20130185072A1 Communication System and Method Between an On-Vehicle Voice Recognition System and an Off-Vehicle Voice Recognition System 有权
标题翻译：车载语音识别系统与车外语音识别系统之间的通信系统与方法
公开(公告)号：US20130185072A1
公开(公告)日：2013-07-18
申请号：US13805921
申请日：2011-06-24
申请人： Ritchie Winson Huang , Pedram Vaghefinazari , Stuart Yamamoto
发明人： Ritchie Winson Huang , Pedram Vaghefinazari , Stuart Yamamoto
IPC分类号： G10L21/06
CPC分类号： G10L15/22 , G10L15/01 , G10L15/30 , G10L17/22 , G10L21/06 , G10L25/72 , G10L2015/223 , G10L2015/228
摘要： A vehicle based system and method for receiving voice inputs and determining whether to perform a voice recognition analysis using in-vehicle resources or resources external to the vehicle.
摘要翻译：一种基于车辆的系统和方法，用于接收语音输入并且确定是否使用车载资源或车辆外部的资源来执行语音识别分析。

9. 发明授权

US09263058B2 Communication system and method between an on-vehicle voice recognition system and an off-vehicle voice recognition system 有权
标题翻译：车载语音识别系统与车外语音识别系统之间的通信系统和方法
公开(公告)号：US09263058B2
公开(公告)日：2016-02-16
申请号：US13805921
申请日：2011-06-24
申请人： Ritchie Winson Huang , Pedram Vaghefinazari , Stuart Yamamoto
发明人： Ritchie Winson Huang , Pedram Vaghefinazari , Stuart Yamamoto
IPC分类号： G10L15/00 , G10L21/00 , G10L25/00 , G10L21/06 , G10L15/30
CPC分类号： G10L15/22 , G10L15/01 , G10L15/30 , G10L17/22 , G10L21/06 , G10L25/72 , G10L2015/223 , G10L2015/228
摘要： A vehicle based system and method for receiving voice inputs and determining whether to perform a voice recognition analysis using in-vehicle resources or resources external to the vehicle.
摘要翻译：一种基于车辆的系统和方法，用于接收语音输入并且确定是否使用车载资源或车辆外部的资源来执行语音识别分析。

10. 发明申请

US20140285664A1 Object Recognition in Low-Lux and High-Lux Conditions 有权
标题翻译：低亮度和高亮度条件下的物体识别
公开(公告)号：US20140285664A1
公开(公告)日：2014-09-25
申请号：US14300569
申请日：2014-06-10
申请人： Pedram Vaghefinazari , Stuart Masakazu Yamamoto , Ritchie Winson Huang , Josh Tyler King , Tarek El Dokor
发明人： Pedram Vaghefinazari , Stuart Masakazu Yamamoto , Ritchie Winson Huang , Josh Tyler King , Tarek El Dokor
IPC分类号： B60R1/00 , G06F3/01 , G06K9/00 , H04N5/235
CPC分类号： G06K9/00335 , B60R1/00 , B60R2300/105 , B60R2300/106 , B60R2300/8006 , G06F3/017 , G06K9/00355 , G06K9/00832 , G06K9/00845 , G06K9/209 , H04N5/232 , H04N5/2351 , H04N5/33
摘要： A system for capturing image data for gestures from a passenger or a driver in a vehicle with a dynamic illumination level comprises a low-lux sensor equipped to capture image data in an environment with an illumination level below an illumination threshold, a high-lux sensor equipped to capture image data in the environment with the illumination level above the illumination threshold, and an object recognition module for activating the sensors. The object recognition module determines the illumination level of the environment and activates the low-lux sensor if the illumination level is below the illumination threshold. If the illumination level is above the threshold, the object recognition module activates the high-lux sensor.
摘要翻译：用于捕获来自具有动态照明级别的车辆中的乘客或驾驶员的手势的图像数据的系统包括：低勒克司传感器，其被配置为在具有低于照明阈值的照度水平的环境中拍摄图像数据;高勒克司传感器用于在照明级别高于照明阈值的环境中拍摄图像数据，以及用于激活传感器的对象识别模块。物体识别模块确定环境的照明水平，并且如果照明水平低于照明阈值，则激活低勒克司传感器。如果照明水平高于阈值，则物体识别模块激活高勒克斯传感器。

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