中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

3 records (took 0.015 seconds)

    APPARATUS WITH ADAPTIVE MICROPHONE CONFIGURATION BASED ON SURFACE PROXIMITY, SURFACE TYPE AND MOTION
    2.
    发明申请
    APPARATUS WITH ADAPTIVE MICROPHONE CONFIGURATION BASED ON SURFACE PROXIMITY, SURFACE TYPE AND MOTION 审中-公开

    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.

    APPARATUS AND METHOD FOR POWER EFFICIENT SIGNAL CONDITIONING FOR A VOICE RECOGNITION SYSTEM
    3.
    发明申请
    APPARATUS AND METHOD FOR POWER EFFICIENT SIGNAL CONDITIONING FOR A VOICE RECOGNITION SYSTEM 审中-公开
    用于语音识别系统的功率有效信号调节的装置和方法

    公开(公告)号：WO2014143438A1

    公开(公告)日：2014-09-18

    申请号：PCT/US2014/014371

    申请日：2014-02-03

    Applicant: MOTOROLA MOBILITY LLC

    Inventor： IVANOV, Plamen A. ,  BASTRY, Kevin J. ,  CLARK, Joel A. ,  JASIUK, Mark A. ,  RAMABADRAN, Tenkasi V. ,  WU, Jincheng,

    IPC: G10L15/20 ,  G10L21/02

    CPC classification number: G10L15/20 ,  G10L15/28 ,  G10L21/0216 ,  G10L21/0364 ,  G10L25/21 ,  G10L2021/02161

    Abstract: A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector (150) on the audio signal in response to the detected change where the voice activity detector (150) is the at least one signal processing component. The method may further include activating and running the noise suppressor (190) only if a noise estimator (160) determines that noise suppression is required. The method may activate and runs a noise type classifier (170) to determine the noise type based on information received from the noise estimator (160) and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms (109), where the selected noise suppressor algorithm is the most power consumption efficient.

    Abstract translation: 所公开的方法包括：监测音频信号能级，同时响应于检测到的音频信号能量级的改变而使多个信号处理组件取消激活并激活至少一个信号处理组件。 该方法可以包括响应于检测到的改变而激活和运行音频信号上的语音活动检测器（150），其中语音活动检测器（150）是至少一个信号处理组件。 该方法还可以包括仅当噪声估计器（160）确定需要噪声抑制时激活和运行噪声抑制器（190）。 该方法可以激活和运行噪声类型分类器（170）以基于从噪声估计器（160）接收的信息来确定噪声类型，并且可以从一组可用的噪声抑制算法（109）中选择噪声抑制算法，其中 所选择的噪声抑制算法是功耗最高的。

Patent Agency Ranking