公开(公告)号：WO2014143448A1

公开(公告)日：2014-09-18

申请号：PCT/US2014/014759

申请日：2014-02-05

Applicant: MOTOROLA MOBILITY LLC

Inventor： ZUREK, Robert A. ,  CLARK, Joel A. ,  DWYER, Joseph C. ,  GARCIA, Juan C. ,  IVANOV, Plamen A. ,  OLIVEIRA, Rivanaldo S. ,  SINGARAJU, Snehitha ,  WU, Jincheng

IPC: G10L25/48 ,  G10L21/02 ,  G10L15/22 ,  G10L15/06 ,  G10L15/20 ,  G10L15/065 ,  G10L21/0208 ,  G10L21/0316 ,  G10L21/0216

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 (102), and capturing (302) at least one acoustic signal using acoustic hardware (218, 224) of the communication device (102), characterizing (304) an acoustic environment external to the communication device (102) using the at least one captured acoustic signal, adapting (306) acoustic processing within the communication device (102) based on the characterized acoustic environment.

Abstract translation: 一种用于在通信设备（102）中适配声学处理的方法和装置，以及使用所述通信设备（102）的声学硬件（218,224）捕获（302）至少一个声学信号，表征（304）声学环境外部 使用所述至少一个捕获的声音信号将所述通信设备（102）发送到所述通信设备（102），基于所述特征的声学环境来适配（306）所述通信设备（102）内的声学处理。

公开(公告)号：WO2014189666A1

公开(公告)日：2014-11-27

申请号：PCT/US2014/036831

申请日：2014-05-05

Applicant: MOTOROLA MOBILITY LLC

Inventor： ZUREK, Robert A. ,  SCHUSTER, Adrian M. ,  SHAU, Fu-Lin ,  WU, Jincheng

IPC: G10L15/22 ,  G10L25/78 ,  G10L15/25 ,  G10L15/24 ,  G10L21/0208 ,  G10L21/0216 ,  G10L15/20

CPC classification number: G10L15/22 ,  B60N2/002 ,  G06F3/013 ,  G06K9/00255 ,  G06K9/00335 ,  G06K9/00597 ,  G06K9/00604 ,  G06K9/00832 ,  G10L15/20 ,  G10L15/24 ,  G10L15/25 ,  G10L15/26 ,  G10L21/0208 ,  G10L25/78 ,  G10L2015/223 ,  G10L2015/227 ,  G10L2021/02166 ,  H04R2430/20 ,  H04R2460/07 ,  H04R2499/11

Abstract: A device performs a method for using image data to aid voice recognition. The method includes the device capturing (302) image data of a vicinity of the device and adjusting (304), based on the image data, a set of parameters for voice recognition performed by the device (102). The set of parameters for the device performing voice recognition include, but are not limited to: a trigger threshold of a trigger for voice recognition; a set of beamforming parameters; a database for voice recognition; and/or an algorithm for voice recognition. The algorithm may include using noise suppression or using acoustic beamforming.

Abstract translation: 设备执行使用图像数据来辅助语音识别的方法。 该方法包括设备捕获（302）设备附近的图像数据，并且基于图像数据调整（304）用于由设备（102）执行的语音识别的一组参数。 执行语音识别的设备的参数集合包括但不限于：用于语音识别的触发的触发阈值; 一组波束成形参数; 用于语音识别的数据库; 和/或用于语音识别的算法。 该算法可以包括使用噪声抑制或使用声波形成。

公开(公告)号：WO2014163780A3

公开(公告)日：2014-10-09

申请号：PCT/US2014/016364

申请日：2014-02-14

Applicant: MOTOROLA MOBILITY LLC

Inventor： IVANOV, Plamen A. ,  BASTYR, Kevin J. ,  CLARK, Joel A. ,  OLIVEIRA, Rivanaldo S. ,  SINGARAJU, Snehitha ,  WU, Jincheng

IPC: H04R3/00 ,  H04R29/00 ,  H04M1/03 ,  G01N29/44

Abstract: An apparatus (100) includes a group of microphones (110) and a surface compensator (200) that is operatively coupled to switch logic (120) and to a signal conditioner (160) that provides a control channel (125) to voice recognition logic (101). The surface compensator (200) may detect surfaces in proximity to the apparatus (100) as well as the surface's acoustic reflectivity or acoustic absorptivity and may accordingly configure the group of microphones (110) including selecting appropriate signal conditioning and beamforming based on the surface acoustic reflectivity or acoustic absorptivity and the orientation of the apparatus (100). Voice recognition (101) performance is thus improved when microphones are impeded or occluded by proximate surfaces. A group of sensors of the apparatus (100) is used by the surface compensator (200) to detect surfaces and surface type, and to determine apparatus (100) orientation and motion.