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

US10880833B2 Smart listening modes supporting quasi always-on listening 有权
公开(公告)号：US10880833B2
公开(公告)日：2020-12-29
申请号：US15463805
申请日：2017-03-20
申请人： Sensory, Incorporated
发明人： Todd F. Mozer , Bryan Pellom
IPC分类号： H04W52/02 , H04W8/24 , G06N20/00
CPC分类号： H04W52/0229 , H04W8/24 , G06N20/00 , Y02D30/70
摘要： Smart listening modes for supporting quasi always-on listening on an electronic device are provided. In one embodiment, the electronic device can determine that a user is likely to utter a voice trigger in order to access the always-on listening functionality of the electronic device. In response to this determination, the electronic device can automatically enable the always-on listening functionality. Similarly, the electronic device can determine that a user is no longer likely to utter the voice trigger in order to access the always-on listening functionality of the electronic device. In response to this second determination, the electronic device can automatically disable the always-on listening functionality.

2. 发明申请

US20140180691A1 SYSTEMS AND METHODS FOR HANDS-FREE VOICE CONTROL AND VOICE SEARCH 审中-公开
标题翻译：无声音语音控制和语音搜索的系统和方法
公开(公告)号：US20140180691A1
公开(公告)日：2014-06-26
申请号：US14184306
申请日：2014-02-19
申请人： SENSORY, INCORPORATED
发明人： Pieter J. Vermeulen , Jonathan Shaw , Todd F. Mozer
IPC分类号： G10L15/22
CPC分类号： G10L15/22 , G10L15/32 , G10L2015/081 , G10L2015/088
摘要： In one embodiment the present invention includes a method comprising receiving an acoustic input signal and processing the acoustic input signal with a plurality of acoustic recognition processes configured to recognize the same target sound. Different acoustic recognition processes start processing different segments of the acoustic input signal at different time points in the acoustic input signal. In one embodiment, initial states in the recognition processes may be configured on each time step.
摘要翻译：在一个实施例中，本发明包括一种方法，包括接收声输入信号并用配置成识别相同目标声音的多个声音识别处理来处理声输入信号。不同的声学识别过程开始在声输入信号的不同时间点处理声输入信号的不同段。在一个实施例中，可以在每个时间步长上配置识别过程中的初始状态。

3. 发明申请

US20130183944A1 Information Access and Device Control Using Mobile Phones and Audio in the Home Environment 有权
标题翻译：在家庭环境中使用移动电话和音频的信息访问和设备控制
公开(公告)号：US20130183944A1
公开(公告)日：2013-07-18
申请号：US13369129
申请日：2012-02-08
申请人： Todd F. Mozer , Forrest S. Mozer
发明人： Todd F. Mozer , Forrest S. Mozer
IPC分类号： G10L21/00 , H04W88/02
CPC分类号： H04L12/282 , G10L15/26 , H04L12/2818
摘要： Embodiments of the present invention are directed toward systems, methods and devices for improving information access to and device control in a home automation environment. Functionality of multiple household device, such as lights, sound, entertainment, HVAC, and communication devices can be activated via voice commands. The voice commands are detected by a nearby control device and relayed via a network communication medium to another control device to which the desired device or system that the user wants to operate is connected. Each control device, disposed throughout the home, can detect a voice command intended for another control box and household device and relay the voice command to the intended control box. In such systems, a user can initiate a telephone call by saying a voice command to a local control box that will forward on the control signal to a mobile phone connected to another control box.
摘要翻译：本发明的实施例涉及用于改善家庭自动化环境中的信息访问和设备控制的系统，方法和设备。可以通过语音命令激活多种家用设备的功能，如灯光，声音，娱乐，暖通空调和通信设备。语音命令由附近的控制设备检测，并通过网络通信介质中继到另一控制设备，用户想要操作的所需设备或系统连接到另一个控制设备。设置在家庭中的每个控制装置可以检测用于另一个控制箱和家用设备的语音命令，并将语音命令中继到预期的控制箱。在这样的系统中，用户可以通过向本地控制箱发出语音命令来发起电话呼叫，该控制箱将控制信号转发到连接到另一控制箱的移动电话。

4. 发明申请

US20090094033A1 Systems and methods of performing speech recognition using historical information 有权
标题翻译：使用历史信息执行语音识别的系统和方法
公开(公告)号：US20090094033A1
公开(公告)日：2009-04-09
申请号：US11973821
申请日：2007-10-09
申请人： Todd F. Mozer , Forrest S. Mozer
发明人： Todd F. Mozer , Forrest S. Mozer
IPC分类号： G10L15/00
CPC分类号： G10L15/22 , G10L2015/227
摘要： Embodiments of the present invention improve speech recognition using historical information. In one embodiment, the present invention includes a method of performing speech recognition comprising receiving an identifier specifying a user of a kiosk, retrieving history information about the user using the identifier, receiving speech input, recognizing said speech input in the context of a first recognition set, resulting in first recognition results, and modifying the first recognition results using the history information.
摘要翻译：本发明的实施例使用历史信息改善语音识别。在一个实施例中，本发明包括执行语音识别的方法，包括：接收指定消息亭用户的标识符，使用标识符检索关于用户的历史信息，接收语音输入，在第一识别的上下文中识别所述语音输入设置，导致第一识别结果，并使用历史信息修改第一识别结果。

5. 发明申请

US20080304360A1 Systems and Methods of Sonic Communication 有权
标题翻译：声音通信系统与方法
公开(公告)号：US20080304360A1
公开(公告)日：2008-12-11
申请号：US12135984
申请日：2008-06-09
申请人： Forrest S. Mozer
发明人： Forrest S. Mozer
IPC分类号： G01S1/72
CPC分类号： H04B11/00
摘要： In one embodiment the present invention includes a method of wireless communication. The method comprises receiving a sonic signal and determining a sequence of sonic tones from a received sonic signal. The receiving includes receiving the sonic signal at an electronic device using a microphone. The sonic signal includes a sequence of sonic tones. The receiving results in the received sonic signal. The sequence of sonic tones contains predefined timing. The timing includes the duration of each sonic tone and a set of intervals between successive sonic tones.
摘要翻译：在一个实施例中，本发明包括无线通信的方法。该方法包括从接收的声音信号接收声音信号和确定声音音调的序列。接收包括使用麦克风在电子设备处接收声音信号。声音信号包括一系列声音音调。收到的结果是接收到的声音信号。声音序列包含预定义的时序。定时包括每个声音的持续时间和连续声音之间的一组间隔。

6. 发明授权

US11004453B2 Avoiding wake word self-triggering 有权
公开(公告)号：US11004453B2
公开(公告)日：2021-05-11
申请号：US15945014
申请日：2018-04-04
申请人： Sensory, Incorporated
发明人： Erich Adams
IPC分类号： G10L15/32 , G10L15/22 , G10L15/30 , G10L15/08
摘要： Techniques for avoiding wake word self-triggering are provided. In one embodiment, an electronic device can receive an audio-out signal to be output as audio via a speaker of the device and can attempt to recognize a wake word in the audio-out signal using a first recognizer. If the wake word is recognized in the audio-out signal, the electronic device can further determine whether a wake word match is made using a second recognizer with respect to a mic-in audio signal captured via a microphone of the device at approximately the same time that the audio-out signal is output via the speaker. If so, the electronic device can ignore the wake word match made using the second recognizer.

7. 发明授权

US10705789B2 Dynamic volume adjustment for virtual assistants 有权
公开(公告)号：US10705789B2
公开(公告)日：2020-07-07
申请号：US16045560
申请日：2018-07-25
申请人： Sensory, Incorporated
发明人： Todd F. Mozer
IPC分类号： G10L15/00 , G06F3/16 , G10L15/22 , G10L25/84 , G06Q50/26 , G10L15/08 , G10L13/00 , G10L13/10 , G10L13/033 , G10L25/21
摘要： Techniques for implementing dynamic volume adjustment by a virtual assistant are provided. In one embodiment, the virtual assistant can receive a voice query or command from a user, recognize the content of the voice query or command, process the voice query or command based on the recognized content, and determine an auditory response to be output to the user. The virtual assistant can then identify a plurality of criteria for automatically determining an output volume level for the response, where the plurality of criteria including content-based criteria and environment-based criteria, calculate values for the plurality of criteria, and combine the values to determine the output volume level. The virtual assistant can subsequently cause the auditory response to be output to the user at the determined output volume level.

8. 发明授权

US09142219B2 Background speech recognition assistant using speaker verification 有权
标题翻译：背景语音识别助手使用说话人验证
公开(公告)号：US09142219B2
公开(公告)日：2015-09-22
申请号：US14280261
申请日：2014-05-16
申请人： Sensory, Incorporated
发明人： Todd F. Mozer
IPC分类号： G10L17/22 , G10L17/00 , G10L15/22
CPC分类号： G10L17/22 , G10L15/22 , G10L17/00 , G10L2015/227
摘要： In one embodiment, a method includes receiving an acoustic input signal at a speech recognizer. A user is identified that is speaking based on the acoustic input signal. The method then determines speaker-specific information previously stored for the user and a set of responses based on the recognized acoustic input signal and the speaker-specific information for the user. It is determined if the response should be output and the response is outputted if it is determined the response should be output.
摘要翻译：在一个实施例中，一种方法包括在语音识别器处接收声输入信号。基于声输入信号识别正在说话的用户。该方法然后基于识别的声输入信号和用户的说话者特定信息确定先前为用户存储的说话者特定信息和一组响应。确定是否应该输出响应，如果确定应该输出响应，则确定响应是否被输出。

9. 发明授权

US08996381B2 Background speech recognition assistant 有权
标题翻译：背景语音识别助手
公开(公告)号：US08996381B2
公开(公告)日：2015-03-31
申请号：US13246666
申请日：2011-09-27
申请人： Todd F. Mozer , Pieter J. Verneulen
发明人： Todd F. Mozer , Pieter J. Verneulen
IPC分类号： G10L21/00 , G10L15/22 , G10L15/32
CPC分类号： G10L15/22 , G10L15/32 , G10L2015/223
摘要： In one embodiment, a method receives an acoustic input signal at a speech recognizer configured to recognize the acoustic input signal in an always on mode. A set of responses based on the recognized acoustic input signal is determined and ranked based on criteria. A computing device determines if the response should be output based on a ranking of the response. The method determines an output method in a plurality of output methods based on the ranking of the response and outputs the response using the output method if it is determined the response should be output.
摘要翻译：在一个实施例中，一种方法在语音识别器处接收声输入信号，该声音输入信号被配置为以常开模式识别声输入信号。基于识别的声输入信号的一组响应被确定并基于标准进行排名。计算装置根据响应的等级确定是否应该输出响应。该方法基于响应的排序来确定多个输出方法中的输出方法，并且如果确定应该输出响应，则使用输出方法输出响应。

10. 发明申请

US20140257812A1 Background Speech Recognition Assistant Using Speaker Verification 审中-公开
标题翻译：背景语音识别助手使用扬声器验证
公开(公告)号：US20140257812A1
公开(公告)日：2014-09-11
申请号：US14280261
申请日：2014-05-16
申请人： Sensory, Incorporated
发明人： Todd F. Mozer
IPC分类号： G10L17/22
CPC分类号： G10L17/22 , G10L15/22 , G10L17/00 , G10L2015/227
摘要： In one embodiment, a method includes receiving an acoustic input signal at a speech recognizer. A user is identified that is speaking based on the acoustic input signal. The method then determines speaker-specific information previously stored for the user and a set of responses based on the recognized acoustic input signal and the speaker-specific information for the user. It is determined if the response should be output and the response is outputted if it is determined the response should be output.
摘要翻译：在一个实施例中，一种方法包括在语音识别器处接收声输入信号。基于声输入信号识别正在说话的用户。该方法然后基于识别的声输入信号和用户的说话者特定信息确定先前为用户存储的说话者特定信息和一组响应。确定是否应该输出响应，如果确定应该输出响应，则确定响应是否被输出。

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