公开(公告)号：US10666417B1

公开(公告)日：2020-05-26

申请号：US16153209

申请日：2018-10-05

Applicant: Amazon Technologies, Inc.

Inventor： Michael Alan Pogue

IPC: H04L7/00 ,  H04W56/00

Abstract: A system capable of synchronizing clocks on separate devices despite variable delays between the separate devices. The system may compensate for skew (e.g., difference between clocks) and drift (e.g., frequency offset between clocks). The system may determine the skew and drift based on differences between timestamps when packets are sent from a first device to a second device and vice versa. For example, the system may estimate a first line corresponding to the fastest packets from the first device to the second device and may estimate a second line corresponding to the fastest packets from the second device to the first device. The system may determine the skew based on a midpoint between the first line and the second line, and the drift based on a slope of the first line or the second line.

公开(公告)号：US10515653B1

公开(公告)日：2019-12-24

申请号：US16114993

申请日：2018-08-28

Applicant: Amazon Technologies, Inc.

Inventor： Michael Alan Pogue ,  Kavitha Velusamy ,  Preethi Parasseri Narayanan ,  Tony David ,  Philip Ryan Hilmes

IPC: G10L25/00

Abstract: A distributed voice controlled system has a primary assistant and at least one secondary assistant. The primary assistant has a housing to hold one or more microphones, one or more speakers, and various computing components. The secondary assistant is similar in structure, but is void of speakers. The voice controlled assistants perform transactions and other functions primarily based on verbal interactions with a user. The assistants within the system are coordinated and synchronized to perform acoustic echo cancellation, selection of a best audio input from among the assistants, and distributed processing.

公开(公告)号：US10325591B1

公开(公告)日：2019-06-18

申请号：US14478923

申请日：2014-09-05

Applicant: Amazon Technologies, Inc.

Inventor： Michael Alan Pogue ,  Kurt Wesley Piersol

IPC: G10L15/20 ,  G10L17/22

Abstract: A speech interface device may capture user speech for analysis by automatic speech recognition (ASR) and natural language understanding (NLU) components. However, an audio signal representing the user speech may also contain interfering sound generated by a media player that is playing audio content such as music. Before performing ASR and NLU, a system attempts to identify the content being played by the media player, such as by querying the media player or by analyzing the audio signal. The system then obtains the same content from an available source and subtracts the audio represented by the content from the audio signal.

公开(公告)号：US10219099B1

公开(公告)日：2019-02-26

申请号：US16041556

申请日：2018-07-20

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Michael Alan Pogue

IPC: H04S7/00 ,  H04R3/12 ,  H04R5/04 ,  G06F17/30 ,  G06F17/18 ,  H04W84/12

Abstract: A group of devices connected on a network operate in conjunction with one another to present content. Individual devices may be wirelessly connected to presentation devices such as speakers. Skew is a delay between when content is sent to the presentation device and then output. Drift is a difference in timing of output between two or more presentation devices not synchronized to a common clock. Non-zero values of skew and drift may result in poor content presentation by the group. An actual rate at which data is transferred to a presentation device is measured and compared to an expected rate. This difference is analyzed to determine a drift value. The content to be delivered to the presentation device is resampled. During presentation the combination of the drift and the resampled content reduces skew. The drift value may also be used to lookup a skew value used to delay initial presentation.

公开(公告)号：US10200724B1

公开(公告)日：2019-02-05

申请号：US15701929

申请日：2017-09-12

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Michael Alan Pogue ,  Kyle Gordon Haight ,  Amit Dubey

IPC: H04N21/233 ,  H04L29/06 ,  H04L12/28

Abstract: Described are techniques for selecting an audio device from a group of devices to function as a master device that receives data from a remote source and distributes the data to other devices within the group. Each device is used for this purpose at least once to determine at least one data throughput value attainable by the device. Based the data throughput values for the devices, signal strength data for the devices, and characteristics of the devices themselves, a master device and a length of time that the audio device is to be used as the master device is determined. Other lengths of time that other devices are to be used temporarily as master devices may also be determined. As additional data throughput values are determined from each instance that a device is used, the determined master device and the lengths of time that each device is used may change.

公开(公告)号：US10097339B1

公开(公告)日：2018-10-09

申请号：US15388258

申请日：2016-12-22

Applicant: Amazon Technologies, Inc.

Inventor： Michael Alan Pogue

IPC: H04L7/00 ,  H04W56/00

Abstract: A system capable of synchronizing clocks on separate devices despite variable delays between the separate devices. The system may compensate for skew (e.g., difference between clocks) and drift (e.g., frequency offset between clocks). The system may determine the skew and drift based on differences between timestamps when packets are sent from a first device to a second device and vice versa. For example, the system may estimate a first line corresponding to the fastest packets from the first device to the second device and may estimate a second line corresponding to the fastest packets from the second device to the first device. The system may determine the skew based on a midpoint between the first line and the second line, and the drift based on a slope of the first line or the second line.

公开(公告)号：US20180233137A1

公开(公告)日：2018-08-16

申请号：US15433953

申请日：2017-02-15

Applicant: Amazon Technologies, Inc.

Inventor： Fred Torok ,  Michael Alan Pogue ,  Vikram Kumar Gundeti ,  Dharini Sundaram

IPC: G10L15/22 ,  G10L13/08 ,  G06F3/16 ,  G10L15/30

CPC classification number: G10L15/22 ,  G06F3/167 ,  G10L13/08 ,  G10L15/183 ,  G10L15/30 ,  G10L2015/025 ,  G10L2015/223

Abstract: A user can utter a voice command in an environment where multiple audio playback devices are located to have audio output on a single device, or a predefined group of devices in a synchronized manner. In instances when the voice command uttered by the user does not specify a target for audio output, an implicit target selection algorithm can evaluate one or more criteria to determine an appropriate target for output of the audio corresponding to the voice command. An example criterion is met if a predetermined time period has lapsed since a last utterance was detected by a device in the environment. However, other criteria can be evaluated for determining a target output device(s).

公开(公告)号：US20180233136A1

公开(公告)日：2018-08-16

申请号：US15433920

申请日：2017-02-15

Applicant: Amazon Technologies, Inc.

Inventor： Fred Torok ,  Michael Alan Pogue ,  Vikram Kumar Gundeti ,  Dharini Sundaram

IPC: G10L15/22 ,  G06F3/16 ,  H04R27/00 ,  H04R3/12 ,  G10L15/30

Abstract: Synchronized output of audio on a group of devices comprises sending audio data from an audio distribution master device to one or more slave devices in the group. In group mode, a slave can be configured to receive audio data directly from a master device acting as a soft wireless access point (WAP) in an environment that includes a traditional WAP. In response to a user request to output audio via the slave in individual mode, the slave may be configured to dynamically switch to receiving audio data via the WAP in the environment without routing the audio data through the master device acting as the soft WAP. This dynamic switching to receiving audio data via the WAP in individual mode can reduce bandwidth consumption on the master device.

公开(公告)号：US09832569B1

公开(公告)日：2017-11-28

申请号：US15369198

申请日：2016-12-05

Applicant: Amazon Technologies, Inc.

Inventor： Robert Ayrapetian ,  Michael Alan Pogue ,  Kenneth Edgar Hild, II

IPC: H04B3/20 ,  H04R3/00

CPC classification number: H04R3/002 ,  G10L21/0208 ,  G10L2021/02082 ,  H04M9/082 ,  H04R3/02

Abstract: A multi-channel echo cancellation system that dynamically adapts to changes in acoustic conditions. The system does not require a sequence of “start-up” tones to determine the impulse responses. Rather, the adaptive filters approximate estimated transfer functions for each channel. A secondary adaptive filter adjusts cancellation to adapt to changes in the actual transfer functions over time after the adaptive filters have been trained, even if the reference signals are not unique relative to each other.

公开(公告)号：US09799329B1

公开(公告)日：2017-10-24

申请号：US14559687

申请日：2014-12-03

Applicant: Amazon Technologies, Inc.

Inventor： Michael Alan Pogue ,  Kurt Wesley Piersol

IPC: G10L15/00 ,  G10L15/20 ,  G10L17/22 ,  G10L25/78 ,  G10L15/06 ,  G10L15/065

CPC classification number: G10L15/20 ,  G10L15/063 ,  G10L15/065 ,  G10L15/22 ,  G10L17/22 ,  G10L21/0208 ,  G10L25/51 ,  G10L25/78

Abstract: This disclosure describes, in part, techniques and devices for identifying recurring environmental sounds in an environment such that these sounds may be canceled out of corresponding audio signals to increase signal-to-noise ratios (SNRs) of the signals and, hence, improve automatic speech recognition (ASR) on the signals. Recurring environmental sounds may include the ringing of a mobile phone, the beeping sound of a microphone, the buzzing of a washing machine, or the like.