公开(公告)号：US20170178664A1

公开(公告)日：2017-06-22

申请号：US15129802

申请日：2015-03-26

Applicant: ANALOG DEVICES, INC.

Inventor： DAVID WINGATE ,  BENJAMIN VIGODA ,  PATRICK OHIOMOBA ,  BRIAN DONNELLY ,  NOAH DANIEL STEIN

IPC: G10L21/0308 ,  G10L25/30 ,  G10L21/0232

CPC classification number: G10L21/0308 ,  G10L15/16 ,  G10L21/0232 ,  G10L21/028 ,  G10L25/30 ,  G10L2021/02166

Abstract: Use of spoken input for user devices, e.g. smartphones, can be challenging due to presence of other sound sources. Blind source separation (BSS) techniques aim to separate a sound generated by a particular source of interest from a mixture of different sounds. Various BSS techniques disclosed herein are based on recognition that providing additional information that is considered within iterations of a nonnegative tensor factorization (NTF) model improves accuracy and efficiency of source separation. Examples of such information include direction estimates or neural network models trained to recognize a particular sound of interest. Furthermore, identifying and processing incremental changes to an NTF model, rather than re-processing the entire model each time data changes, provides an efficient and fast manner for performing source separation on large sets of quickly changing data. Carrying out at least parts of BSS techniques in a cloud allows flexible utilization of local and remote sources.

公开(公告)号：US20170017892A1

公开(公告)日：2017-01-19

申请号：US15154113

申请日：2014-10-15

Applicant: ANALOG DEVICES, INC.

Inventor： JEFFREY G. BERNSTEIN ,  DAVID WINGATE ,  JOHN REDFORD

IPC: G06N7/00

CPC classification number: G06N7/005 ,  G06F17/18

Abstract: The disclosed apparatus and methods include a reconfigurable sampling accelerator and a method of using the reconfigurable sampling accelerator, respectively. The reconfigurable sampling accelerator can be adapted to a variety of target applications. The reconfigurable sampling accelerator can include a sampling module, a memory system, and a controller that is configured to coordinate operations in the sampling module and the memory system. The sampling module can include a plurality of sampling units, and the plurality of sampling units can be configured to generate samples in parallel. The sampling module can leverage inherent characteristics of a probabilistic model to generate samples in parallel.

Abstract translation: 所公开的装置和方法分别包括可重构采样加速器和使用可重构采样加速器的方法。 可重构采样加速器可适用于各种目标应用。 可重构采样加速器可以包括采样模块，存储器系统和被配置为协调采样模块和存储器系统中的操作的控制器。 采样模块可以包括多个采样单元，并且多个采样单元可被配置为并行地产生采样。 抽样模块可以利用概率模型的固有特征来并行生成样本。

公开(公告)号：US20170243577A1

公开(公告)日：2017-08-24

申请号：US15505736

申请日：2015-08-27

Applicant: Analog Devices, Inc.

Inventor： DAVID WINGATE

IPC: G10L15/20 ,  H04R1/40 ,  H04R3/00 ,  G10L21/0216 ,  G10L21/0272 ,  G10L15/22 ,  G10L25/84

CPC classification number: G10L15/20 ,  G10L15/01 ,  G10L15/22 ,  G10L21/0208 ,  G10L21/0216 ,  G10L21/0272 ,  G10L25/84 ,  G10L2015/223 ,  G10L2021/02166 ,  H04R1/406 ,  H04R3/00 ,  H04R3/005 ,  H04R2410/00 ,  H04R2410/01 ,  H04R2499/11 ,  H04R2499/13

Abstract: The present disclosure relates generally to improving audio processing using an intelligent microphone and, more particularly, to techniques for processing audio received at a microphone with integrated analog-to-digital conversion, digital signal processing, acoustic source separation, and for further processing by a speech recognition system. Embodiments of the present disclosure include intelligent microphone systems designed to collect and process high-quality audio input efficiently. Systems and method for audio processing using an intelligent microphone include an integrated package with one or more microphones, analog-to-digital converters (ADCs), digital signal processors (DSPs), source separation modules, memory, and automatic speech recognition. Systems and methods are also provided for audio processing using an intelligent microphone that includes a microphone array and uses a preprogrammed audio beamformer calibrated to the included microphone array.

公开(公告)号：US20160071526A1

公开(公告)日：2016-03-10

申请号：US14847818

申请日：2015-09-08

Applicant: ANALOG DEVICES, INC.

Inventor： DAVID WINGATE ,  NOAH DANIEL STEIN ,  BENJAMIN VIGODA ,  PATRICK OHIOMOBA ,  BRIAN DONNELLY

IPC: G10L21/028 ,  G10L25/84 ,  G10L19/022 ,  G01S3/802 ,  G10L21/0232 ,  G10L21/0264

CPC classification number: G10L21/028 ,  G01S3/802 ,  G01S3/807

Abstract: The present disclosure relates generally to improving acoustic source tracking and selection and, more particularly, to techniques for acoustic source tracking and selection using motion or position information. Embodiments of the present disclosure include systems designed to select and track acoustic sources. In one embodiment, the system may be realized as an integrated circuit including a microphone array, motion sensing circuitry, position sensing circuitry, analog-to-digital converter (ADC) circuitry configured to convert analog audio signals from the microphone array into digital audio signals for further processing, and a digital signal processor (DSP) or other circuitry for processing the digital audio signals based on motion data and other sensor data. Sensor data may be correlated to the analog or digital audio signals to improve source separation or other audio processing.

Abstract translation: 本公开一般涉及改进声源跟踪和选择，更具体地，涉及使用运动或位置信息进行声源跟踪和选择的技术。 本公开的实施例包括被设计为选择和跟踪声源的系统。 在一个实施例中，该系统可被实现为包括麦克风阵列，运动感测电路，位置感测电路，被配置为将来自麦克风阵列的模拟音频信号转换成数字音频信号的模数转换器（ADC）电路的集成电路 用于进一步处理，以及用于基于运动数据和其他传感器数据处理数字音频信号的数字信号处理器（DSP）或其它电路。 传感器数据可以与模拟或数字音频信号相关联，以改善源分离或其他音频处理。

公开(公告)号：US20160371977A1

公开(公告)日：2016-12-22

申请号：US15121435

申请日：2015-02-26

Applicant: ANALOG DEVICES, INC.

Inventor： DAVID WINGATE ,  HARVEY WEINBERG ,  BENJAMIN VIGODA

IPC: G08G1/0968 ,  G07C5/00 ,  G10L15/22 ,  B60W50/10 ,  G01C21/34 ,  H04R3/04 ,  G08G1/01 ,  B60W50/16

CPC classification number: G08G1/096866 ,  B60W30/16 ,  B60W40/08 ,  B60W50/10 ,  B60W50/16 ,  B60W2040/089 ,  B60W2420/42 ,  B60W2420/52 ,  B60W2420/54 ,  B60W2540/02 ,  B60W2540/04 ,  B60W2550/12 ,  B60W2550/14 ,  B60W2550/147 ,  B60W2550/40 ,  B60W2550/404 ,  B60W2750/40 ,  G01C21/3492 ,  G01C21/3691 ,  G07C5/008 ,  G08G1/0112 ,  G08G1/0133 ,  G08G1/0145 ,  G08G1/096816 ,  G08G1/096844 ,  G10L15/22 ,  G10L15/30 ,  G10L21/0216 ,  H04R3/04 ,  H04R2499/13

Abstract: A system is provided for updated processing of audio signals in a vehicle. The system includes a microphone, a transceiver and head unit. The microphone receives audio signals. The transceiver sends the received audio signals to a cloud computing system for processing, and receives the processed audio signals from the cloud computing system. The head unit receives the processed audio signals from the transceiver and plays the processed audio data through the vehicle's audio system.

Abstract translation: 提供一种用于车辆中音频信号的更新处理的系统。 该系统包括麦克风，收发器和头单元。 麦克风接收音频信号。 收发器将接收到的音频信号发送到云计算系统进行处理，并从云计算系统接收经处理的音频信号。 头单元从收发器接收经处理的音频信号，并通过车辆的音频系统播放经处理的音频数据。

公开(公告)号：US20160354038A1

公开(公告)日：2016-12-08

申请号：US15170373

申请日：2016-06-01

Applicant: ANALOG DEVICES, INC.

Inventor： SEFA DEMIRTAS ,  ROBERT ADAMS ,  JEFFREY G. BERNSTEIN ,  NOAH DANIEL STEIN ,  DAVID WINGATE

IPC: A61B5/00 ,  A61B5/0245 ,  A61B5/0255 ,  A61B5/024

CPC classification number: A61B5/721 ,  A61B5/02416 ,  A61B5/02438 ,  A61B5/725 ,  A61B2562/0219

Abstract: Heart rate monitors are plagued by noisy photoplethysmography (PPG) data, which makes it difficult for the monitors to output a consistently accurate heart rate reading. Noise is often caused by motion. Using known methods for processing accelerometer readings that measure movement to filter out some of this noise may help, but not always. The present disclosure describes an improved filtering approach, referred to herein as an iterative frequency-domain mask estimation technique, based on using frequency-domain representation (e.g. STFT) of PPG data and accelerometer data for each accelerometer channel to generate filters for filtering the PPG signal from motion-related artifacts prior to tracking frequency of the heartbeat (heart rate). Implementing this technique leads to more accurate heart rate measurements.

Abstract translation: 心率监测器受到嘈杂的光谱体积描记术（PPG）数据的困扰，使得监测仪难以输出一致的心率读数。 噪音通常由运动引起。 使用已知的处理加速度计读数的方法来测量移动以滤除某些噪声可能有助于，但不总是。 本公开描述了基于使用PPG数据的频域表示（例如STFT）和每个加速度计通道的加速度计数据来生成用于过滤PPG的滤波器的改进的滤波方法（这里称为迭代频域掩模估计技术） 在跟踪心跳频率（心率）之前的运动相关假象的信号。 实施这种技术导致更准确的心率测量。