公开(公告)号：US10733990B2

公开(公告)日：2020-08-04

申请号：US15884353

申请日：2018-01-30

Applicant: MOTOROLA MOBILITY LLC

Inventor： Robert A. Zurek ,  Pratik M. Kamdar ,  Jincheng Wu ,  Joel Clark

IPC: G10L15/00 ,  G10L15/22 ,  G10L15/08

Abstract: A method, a system, and a computer program product for preventing initiation of a voice recognition session. The method includes monitoring at least one audio output channel for at least one audio trigger phrase that initiates a voice recognition session. The method further includes in response to detecting the at least one audio trigger phrase on the at least one audio output channel, setting a logic state of at least one output trigger detector of the at least one audio output channel to a first state. The method further includes gating a logic state of at least one input trigger detector of at least one audio input channel to the first state for a time period and preventing initiation of a voice recognition session by the at least one audio trigger phrase on the at least one audio input channel while the logic state is the first state.

公开(公告)号：US10665234B2

公开(公告)日：2020-05-26

申请号：US15883368

申请日：2018-01-30

Applicant: MOTOROLA MOBILITY LLC

Inventor： Robert A. Zurek ,  Pratik M. Kamdar ,  Jincheng Wu ,  Joel Clark ,  Plamen Ivanov

IPC: G10L15/22 ,  G06F3/16 ,  G10L17/22 ,  H04R1/40 ,  H04R3/00

Abstract: A method, a system, and a computer program product for detecting an audio trigger phrase at a particular audio input channel and initiating a voice recognition session. The method includes capturing audio content by a plurality of microphone pairs of an audio capturing device, wherein each microphone pair of the plurality of microphone pairs is associated with an audio input channel of a plurality of audio input channels of the audio capturing device. The method further includes simultaneously monitoring, by a processor of the audio capturing device, audio content on each of the audio input channels. The method further includes: independently detecting, by the processor, an audio trigger phrase on at least one audio input channel of the plurality of audio input channels; and in response to detecting the audio trigger phrase, commencing a voice recognition session using the at least one audio input channel as an audio source.

公开(公告)号：US20150131966A1

公开(公告)日：2015-05-14

申请号：US14319209

申请日：2014-06-30

Applicant: MOTOROLA MOBILITY LLC

Inventor： Robert A. Zurek ,  Thomas Y. Merrell

IPC: G11B20/10 ,  H04S7/00 ,  H04S3/00

CPC classification number: H04S3/008 ,  H04S2400/11 ,  H04S2420/13

Abstract: Three-dimensional (3D) audio content creation and rendering systems and methodologies are presented here. A disclosed method of processing 3D audio assigns audio source objects to 3D video objects, links audio tracks to assigned audio source objects, and performs wave field synthesis on the linked audio tracks to generate 3D audio data representing a 3D spatial sound field. A disclosed method of processing 3D audio during playback of 3D video content obtains 3D audio data and 3D video data for a frame of 3D video content, applies device-specific parameters to the 3D audio data to obtain transformed 3D audio data scaled to a presentation device, and processes the transformed 3D audio data to render audio information for an array of speakers associated with the presentation device.

Abstract translation: 这里介绍了三维（3D）音频内容创建和渲染系统和方法。 所公开的处理3D音频的方法将音频源对象分配给3D视频对象，将音轨链接到分配的音频源对象，并且在链接的音轨上执行波场合成，以生成表示3D空间声场的3D音频数据。 一种公开的在3D视频内容播放期间处理3D音频的方法获得用于3D视频内容的帧的3D音频数据和3D视频数据，将特定于设备的参数应用于3D音频数据，以获得缩放到呈现设备的经变换的3D音频数据 并且处理变换的3D音频数据以呈现与呈现设备相关联的扬声器阵列的音频信息。

公开(公告)号：US20130021503A1

公开(公告)日：2013-01-24

申请号：US13626551

申请日：2012-09-25

Applicant: Motorola Mobility LLC

Inventor： Robert A. Zurek ,  Kevin J. Bastyr ,  Joel A. Clark ,  Plamen A. Ivanov

IPC: H04R3/00 ,  H04N5/232 ,  H04N5/225

CPC classification number: H04R1/406 ,  H04R2201/401 ,  H04R2430/01 ,  H04R2499/11

Abstract: An electronic apparatus is provided that has a rear-side and a front-side, a first microphone that generates a first signal, and a second microphone that generates a second signal. An automated balance controller generates a balancing signal based on a proximity sensor signal. A processor processes the first and second signals to generate at least one beamformed audio signal, where an audio level difference between a front-side gain and a rear-side gain of the beamformed audio signal is controlled during processing based on the balancing signal.

Abstract translation: 提供一种电子设备，其具有后侧和前侧，产生第一信号的第一麦克风和产生第二信号的第二麦克风。 自动平衡控制器基于接近传感器信号产生平衡信号。 A处理器处理第一和第二信号以产生至少一个波束形成的音频信号，其中基于平衡信号在处理期间控制波束形成的音频信号的前侧增益和后侧增益之间的音频电平差。

公开(公告)号：US20140278395A1

公开(公告)日：2014-09-18

申请号：US13956131

申请日：2013-07-31

Applicant: Motorola Mobility LLC

Inventor： Robert A. Zurek ,  Kevin J. Bastyr ,  Giles T. Davis ,  Plamen A. Ivanov ,  Adrian M. Schuster

IPC: G10L15/065

CPC classification number: G10L15/065 ,  G10L15/20 ,  G10L21/003 ,  G10L21/0208 ,  G10L21/0316 ,  G10L21/04 ,  G10L2015/226

Abstract: A method and apparatus for determining a motion environment profile to adapt voice recognition processing includes a device receiving an acoustic signal including a speech signal, which is provided to a voice recognition module. The method also includes determining a motion profile for the device, determining a temperature profile for the device, and determining a noise profile for the acoustic signal. The method further includes determining, from the motion, temperature, and noise profiles, a motion environment profile for the device and adapting voice recognition processing for the speech signal based on the motion environment profile.

Abstract translation: 用于确定运动环境分布以适应语音识别处理的方法和装置包括接收包括提供给语音识别模块的语音信号的声信号的装置。 该方法还包括确定装置的运动曲线，确定装置的温度曲线，以及确定声信号的噪声分布。 该方法还包括根据运动，温度和噪声分布来确定装置的运动环境简档，以及基于运动环境分布调整语音信号的语音识别处理。

公开(公告)号：US20140278420A1

公开(公告)日：2014-09-18

申请号：US14094875

申请日：2013-12-03

Applicant: Motorola Mobility LLC

Inventor： John R. Meloney ,  Joel A. Clark ,  Joseph C. Dwyer ,  Adrian M. Schuster ,  Snehitha Singaraju ,  Robert A. Zurek

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G10L15/20

Abstract: An electronic device digitally combines a single voice input with each of a series of noise samples. Each noise sample is taken from a different audio environment (e.g., street noise, babble, interior car noise). The voice input/noise sample combinations are used to train a voice recognition model database without the user having to repeat the voice input in each of the different environments. In one variation, the electronic device transmits the user's voice input to a server that maintains and trains the voice recognition model database.

Abstract translation: 电子设备将单个语音输入与一系列噪声样本中的每一个进行数字组合。 每个噪声样本都是从不同的音频环境中获取的（例如，街道噪音，混音，车内噪音）。 语音输入/噪声样本组合用于训练语音识别模型数据库，而用户不必在每个不同环境中重复语音输入。 在一个变型中，电子设备将用户的语音输入传送到维护和训练语音识别模型数据库的服务器。

公开(公告)号：US20140278416A1

公开(公告)日：2014-09-18

申请号：US13955719

申请日：2013-07-31

Applicant: Motorola Mobility LLC

Inventor： Adrian M. Schuster ,  Joel A. Clark ,  Giles T. Davis ,  Plamen A. Ivanov ,  Robert A. Zurek

IPC: G10L17/00

CPC classification number: G10L17/00 ,  G10L15/32

Abstract: A method and apparatus for voice recognition performed in a voice recognition block comprising a plurality of voice recognition stages. The method includes receiving a first plurality of voice inputs, corresponding to a first phrase, into a first voice recognition stage of the plurality of voice recognition stages, wherein multiple ones of the voice recognition stages includes a plurality of voice recognition modules and multiples ones of the voice recognition stages perform a different type of voice recognition processing, wherein the first voice recognition stage processes the first plurality of voice inputs to generate a first plurality of outputs for receipt by a subsequent voice recognition stage. The method further includes, receiving by each subsequent voice recognition stage a plurality of outputs from a preceding voice recognition stage, wherein a plurality of final outputs is generated by a final voice recognition stage from which to approximate the first phrase.

Abstract translation: 一种用于在包括多个语音识别级的语音识别块中​​执行的用于语音识别的方法和装置。 该方法包括：将与第一短语相对应的第一多个语音输入接收到多个语音识别阶段的第一语音识别阶段，其中多个语音识别阶段包括多个语音识别模块和多个语音识别模块 语音识别阶段执行不同类型的语音识别处理，其中第一语音识别阶段处理第一多个语音输入以产生第一多个输出以便通过后续语音识别阶段接收。 该方法还包括：通过每个随后的语音识别级接收来自前一语音识别级的多个输出，其中通过最终语音识别级产生多个最终输出以从其近似第一短语。

公开(公告)号：US20140274212A1

公开(公告)日：2014-09-18

申请号：US13956076

申请日：2013-07-31

Applicant: Motorola Mobility LLC

Inventor： Robert A. Zurek ,  Joel A. Clark ,  Joseph C. Dwyer ,  Juan C. Garcia ,  Plamen A. Ivanov ,  Rivanaldo S. Oliveira ,  Snehitha Singaraju ,  Jincheng Wu

IPC: H04M1/60 ,  G10L15/20

CPC classification number: H04M1/6041 ,  G01S15/08 ,  G10L15/06 ,  G10L15/063 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L21/02 ,  G10L21/0316 ,  G10L25/48 ,  G10L2015/228 ,  G10L2021/02082 ,  G10L2021/02161 ,  H03G3/32 ,  H04M1/271

Abstract: A method and apparatus for adapting acoustic processing in a communication device, and capturing at least one acoustic signal using acoustic hardware of the communication device, characterizing an acoustic environment external to the communication device using the at least one captured acoustic signal, adapting acoustic processing within the communication device based on the characterized acoustic environment.

Abstract translation: 一种用于调整通信设备中的声学处理的方法和装置，以及使用所述通信设备的声学硬件捕获至少一个声学信号，其特征在于，使用所述至少一个捕获的声学信号对所述通信设备外部的声学环境进行表征， 基于特征声学环境的通信设备。

公开(公告)号：US20140270248A1

公开(公告)日：2014-09-18

申请号：US13946150

申请日：2013-07-19

Applicant: Motorola Mobility LLC

Inventor： Plamen A. Ivanov ,  Rivanaldo S. Oliveira ,  Robert A. Zurek

IPC: H04R3/00

CPC classification number: H04R3/005 ,  H04M1/605 ,  H04R2499/11

Abstract: A method for controlling the orientation of a virtual microphone, which is carried out on an electronic device, includes combining and processing signals from a microphone array to create a virtual microphone; receiving data from a sensor of the electronic device; determining, based on the received data, a mode in which the electronic device is being used; and based on the determined mode, directionally orienting the virtual microphone. Possible use modes include a) a stowed use mode, in which the criterion is the electronic device being substantially enclosed by surrounding material; b) a handset (alternately, private) use mode, in which the criterion is the electronic device being held proximate to a user; and c) a handheld (alternately, speakerphone) use mode, in which the criterion is the electronic device being held away from a user.

Abstract translation: 一种用于控制在电子设备上执行的虚拟麦克风的取向的方法包括组合和处理来自麦克风阵列的信号以创建虚拟麦克风; 从所述电子设备的传感器接收数据; 基于所接收的数据确定使用所述电子设备的模式; 并且基于确定的模式，定向地定向虚拟麦克风。 可能的使用模式包括：a）存放使用模式，其中标准是电子设备被围绕的材料基本上包围; b）手机（交替的，私人的）使用模式，其中所述标准是电子设备被保持靠近用户; 以及c）手持（交替地，免提电话）使用模式，其中标准是远离使用者的电子设备。

公开(公告)号：US09462257B2

公开(公告)日：2016-10-04

申请号：US14035984

申请日：2013-09-25

Applicant: MOTOROLA MOBILITY LLC

Inventor： Robert A. Zurek ,  Timothy Dickinson

IPC: G06T15/08 ,  H04N13/02 ,  G06T7/00

CPC classification number: H04N13/264 ,  G06T7/593 ,  G06T2207/10012 ,  G06T2207/20056

Abstract: A method and apparatus provide two-dimensional to three-dimensional image conversion. The apparatus can include an input configured to receive a first image. The apparatus can include a controller configured to segment the first image into a plurality of regions, configured to perform a Fast Fourier Transform on at least one of the regions, and configured to determine a relative horizontal displacement distance between a first frame and a second frame of at least one region based on performing the Fast Fourier Transform.

Abstract translation: 一种方法和装置提供二维至三维图像转换。 该装置可以包括被配置为接收第一图像的输入。 该装置可以包括被配置为将第一图像分割成多个区域的控制器，其被配置为在至少一个区域上执行快速傅立叶变换，并且被配置为确定第一帧和第二帧之间的相对水平位移距离 基于执行快速傅里叶变换的至少一个区域。