公开(公告)号：US20180286414A1

公开(公告)日：2018-10-04

申请号：US15475329

申请日：2017-03-31

申请人： Binuraj K. Ravindran ,  Francis M. Tharappel ,  Prabhakar R. Datta ,  Tobias Bocklet ,  Maciej Muchlinski ,  Tomasz Dorau ,  Josef G. Bauer ,  Saurin Shah ,  Georg Stemmer

发明人： Binuraj K. Ravindran ,  Francis M. Tharappel ,  Prabhakar R. Datta ,  Tobias Bocklet ,  Maciej Muchlinski ,  Tomasz Dorau ,  Josef G. Bauer ,  Saurin Shah ,  Georg Stemmer

IPC分类号： G10L19/002 ,  G10L15/02 ,  G10L15/08 ,  G10L19/032 ,  G10L25/24

CPC分类号： G10L25/24 ,  G10L15/02 ,  G10L15/08 ,  G10L15/30 ,  G10L19/032 ,  G10L25/78 ,  G10L2015/088 ,  H04W4/80

摘要： Methods, apparatus, systems and articles of manufacture are disclosed for distributed automatic speech recognition. An example apparatus includes a detector to process an input audio signal and identify a portion of the input audio signal including a sound to be evaluated, the sound to be evaluated organized into a plurality of audio features representing the sound. The example apparatus includes a quantizer to process the audio features using a quantization process to reduce the audio features to generate a reduced set of audio features for transmission. The example apparatus includes a transmitter to transmit the reduced set of audio features over a low-energy communication channel for processing.

公开(公告)号：US10373630B2

公开(公告)日：2019-08-06

申请号：US15475329

申请日：2017-03-31

申请人： Binuraj K. Ravindran ,  Francis M. Tharappel ,  Prabhakar R. Datta ,  Tobias Bocklet ,  Maciej Muchlinski ,  Tomasz Dorau ,  Josef G. Bauer ,  Saurin Shah ,  Georg Stemmer

发明人： Binuraj K. Ravindran ,  Francis M. Tharappel ,  Prabhakar R. Datta ,  Tobias Bocklet ,  Maciej Muchlinski ,  Tomasz Dorau ,  Josef G. Bauer ,  Saurin Shah ,  Georg Stemmer

IPC分类号： G10L15/30 ,  G10L25/24 ,  G10L15/08 ,  G10L15/02 ,  G10L19/032 ,  H04W4/80 ,  G10L25/78

摘要： Methods, apparatus, systems and articles of manufacture are disclosed for distributed automatic speech recognition. An example apparatus includes a detector to process an input audio signal and identify a portion of the input audio signal including a sound to be evaluated, the sound to be evaluated organized into a plurality of audio features representing the sound. The example apparatus includes a quantizer to process the audio features using a quantization process to reduce the audio features to generate a reduced set of audio features for transmission. The example apparatus includes a transmitter to transmit the reduced set of audio features over a low-energy communication channel for processing.

公开(公告)号：US20140270197A1

公开(公告)日：2014-09-18

申请号：US13841166

申请日：2013-03-15

申请人： Lakshman Krishnamurthy ,  Michael E. Deisher ,  Francis M. Tharappel ,  Prabhakar R. Datta

发明人： Lakshman Krishnamurthy ,  Michael E. Deisher ,  Francis M. Tharappel ,  Prabhakar R. Datta

IPC分类号： H04R3/00

CPC分类号： H04M1/6008 ,  H04M1/6041 ,  H04M2250/74

摘要： Systems and methods may provide for using an audio front end of a mobile device to sampled audio from an audio signal during a first portion of a periodic detection window, and reducing a power consumption of one or more components of the audio front end during a second portion of the periodic detection window. Additionally, a determination may be made as to whether voice activity is present in the audio signal based at least in part on the sampled audio. In one example, the length of the first portion and the length of the second portion are defined by a duty cycle of the periodic detection window.

摘要翻译： 系统和方法可以提供在周期性检测窗口的第一部分期间使用移动设备的音频前端来自音频信号的采样音频，并且在第二时间段期间减少音频前端的一个或多个组件的功率消耗 周期性检测窗口的一部分。 另外，可以至少部分地基于采样的音频来确定语音活动是否存在于音频信号中。 在一个示例中，第一部分的长度和第二部分的长度由周期性检测窗口的占空比限定。

公开(公告)号：US09270801B2

公开(公告)日：2016-02-23

申请号：US13841166

申请日：2013-03-15

申请人： Lakshman Krishnamurthy ,  Michael E. Deisher ,  Francis M. Tharappel ,  Prabhakar R. Datta

发明人： Lakshman Krishnamurthy ,  Michael E. Deisher ,  Francis M. Tharappel ,  Prabhakar R. Datta

IPC分类号： H04R29/00 ,  H04M1/60

CPC分类号： H04M1/6008 ,  H04M1/6041 ,  H04M2250/74

摘要： Systems and methods may provide for using an audio front end of a mobile device to sampled audio from an audio signal during a first portion of a periodic detection window, and reducing a power consumption of one or more components of the audio front end during a second portion of the periodic detection window. Additionally, a determination may be made as to whether voice activity is present in the audio signal based at least in part on the sampled audio. In one example, the length of the first portion and the length of the second portion are defined by a duty cycle of the periodic detection window.

摘要翻译： 系统和方法可以提供在周期性检测窗口的第一部分期间使用移动设备的音频前端来自音频信号的采样音频，并且在第二时间段期间减少音频前端的一个或多个组件的功率消耗 周期性检测窗口的一部分。 另外，可以至少部分地基于采样的音频来确定语音活动是否存在于音频信号中。 在一个示例中，第一部分的长度和第二部分的长度由周期性检测窗口的占空比限定。