MULTI-MICROPHONE NEURAL NETWORK FOR SOUND RECOGNITION

    公开(公告)号:US20170325023A1

    公开(公告)日:2017-11-09

    申请号:US14988047

    申请日:2016-01-05

    Applicant: Google Inc.

    Abstract: A neural network is provided for recognition and enhancement of multi-channel sound signals received by multiple microphones, which need not be aligned in a linear array in a given environment. Directions and distances of sound sources may also be detected by the neural network without the need for a beamformer connected to the microphones. The neural network may be trained by knowledge gained from free-field array impulse responses obtained in an anechoic chamber, array impulse responses that model simulated environments of different reverberation times, and array impulse responses obtained in actual environments.

    MICROPHONE PLACEMENT FOR SOUND SOURCE DIRECTION ESTIMATION
    145.
    发明申请
    MICROPHONE PLACEMENT FOR SOUND SOURCE DIRECTION ESTIMATION 有权
    麦克风放置用于声源方向估计

    公开(公告)号:US20170070814A1

    公开(公告)日:2017-03-09

    申请号:US14848703

    申请日:2015-09-09

    Abstract: Architectures of numbers of microphones and their positioning in a device for sound source direction estimation and source separation are presented. The directions of sources are front, back, left, right, top, and bottom of the device, and can be determined by amplitude and phase differences of microphone signals with proper microphone positioning. The source separation is to separate the sound coming from different directions from the mix of sources in microphone signals. This can be done with blind source separation (BSS), independent component analysis (ICA), and beamforming (BF) technologies. The device can perform many kinds of audio enhancements for the device. For example, it can perform noise reduction for communications; it can choose a source from a desired direction to perform speech recognition; and it can correct sound perceiving directions in microphones and generate desired sound images like stereo audio output. In addition, with source separation, 2.1, 5.1, 7.1, and other audio encoding and surround sound effects can be straightforward.

    Abstract translation: 介绍了麦克风数量及其在声源方向估计和信号源分离装置中的定位结构。 源的方向是设备的前置,后端,左侧,右侧,顶部和底部,可以通过适当的麦克风定位的麦克风信号的幅度和相位差来确定。 源分离是将来自不同方向的声音与麦克风信号中的声源混合分离。 这可以通过盲源分离(BSS),独立分量分析(ICA)和波束成形(BF)技术来完成。 该设备可以为设备执行多种音频增强功能。 例如,它可以进行通信的降噪; 它可以从期望的方向选择一个源来执行语音识别; 并且它可以校正麦克风中的声音感知方向,并产生所需的声像,如立体声音频输出。 另外,随着源分离,2.1,5.1,7.1等音频编码和环绕声效果可以直观的体现出来。

    ARRAY MICROPHONE SYSTEM AND METHOD OF ASSEMBLING THE SAME
    147.
    发明申请
    ARRAY MICROPHONE SYSTEM AND METHOD OF ASSEMBLING THE SAME 有权
    阵列麦克风系统及其组装方法

    公开(公告)号:US20160323668A1

    公开(公告)日:2016-11-03

    申请号:US14701376

    申请日:2015-04-30

    Abstract: Embodiments include a microphone assembly comprising an array microphone and a housing configured to support the array microphone and sized and shaped to be mountable in a drop ceiling in place of at least one of a plurality of ceiling tiles included in the drop ceiling. A front face of the housing includes a sound-permeable screen having a size and shape that is substantially similar to the at least one of the plurality of ceiling tiles. Embodiments also include an array microphone system comprising a plurality of microphones arranged, on a substrate, in a number of concentric, nested rings of varying sizes around a central point of the substrate. Each ring comprises a subset of the plurality of microphones positioned at predetermined intervals along a circumference of the ring.

    Abstract translation: 实施例包括麦克风组件,其包括阵列麦克风和壳体,其被配置为支撑阵列麦克风,并且其尺寸和形状可安装在落地天花板中,代替包括在落地天花板中的多个天花板瓦片中的至少一个。 壳体的前表面包括具有基本上类似于多个天花板瓦片中的至少一个的大小和形状的透声屏幕。 实施例还包括阵列麦克风系统,其包括多个麦克风,所述多个麦克风在基板上布置在围绕基板的中心点的多个不同大小的同心嵌套的环中。 每个环包括沿着环的圆周以预定间隔定位的多个麦克风的子集。

    Microphone support device for sound source localization
    148.
    发明授权
    Microphone support device for sound source localization 有权
    用于声源定位的麦克风支持设备

    公开(公告)号:US09462362B2

    公开(公告)日:2016-10-04

    申请号:US14775062

    申请日:2014-01-31

    Abstract: A microphone support device includes a ring-shaped flame, a plurality of fixed arms which protrude toward an inner side of the flame, a plurality of movable arms which are longer than the fixed arms and are detachable, and multiple microphones. A small-size microphone array is constructed by accommodating the plurality of movable arms inside of the flame in a radiating state. On the other hand, a large-size microphone array is constructed by radially developing the plurality of movable arms outside of the flame. When constructing a circular two-dimensional microphone array, a size of the circular two-dimensional microphone array can be easily changed in this manner. Hence, the sound localization can be handled over a wide frequency range.

    Abstract translation: 麦克风支撑装置包括环形火焰,朝向火焰内侧突出的多个固定臂,多个可移动臂,其比固定臂长并且可拆卸,并且具有多个麦克风。 通过以散热状态容纳多个可动臂在火焰内部构成小尺寸的麦克风阵列。 另一方面,通过在火焰外部径向显影多个活动臂来构造大尺寸麦克风阵列。 当构造圆形二维麦克风阵列时,可以容易地以这种方式改变圆形二维麦克风阵列的尺寸。 因此,可以在宽的频率范围内处理声音定位。

    Method and Apparatus for Determining the Direction of Arrival of a Sonic Boom
    150.
    发明申请
    Method and Apparatus for Determining the Direction of Arrival of a Sonic Boom 有权
    确定声波扬声器到达方向的方法和装置

    公开(公告)号:US20160216357A1

    公开(公告)日:2016-07-28

    申请号:US14604088

    申请日:2015-01-23

    Abstract: A method and apparatus for determining a direction of arrival of an acoustic event of interest that arrives at an array. Data acquired from the array is received. A portion of the data that represents an acoustic signature for the acoustic event of interest is identified. An azimuth angle may be computed for an acoustic event using the portion of the data identified. An elevation angle for the acoustic event is computed using a beamforming process customized based on the azimuth angle computed.

    Abstract translation: 一种用于确定到达阵列的感兴趣的声学事件的到达方向的方法和装置。 接收从阵列获取的数据。 识别表示感兴趣的声学事件的声学签名的数据的一部分。 可以使用识别的数据的部分来计算声学事件的方位角。 使用基于所计算的方位角定制的波束形成过程来计算声学事件的仰角。

Patent Agency Ranking