-
公开(公告)号:US10986444B2
公开(公告)日:2021-04-20
申请号:US16798706
申请日:2020-02-24
Applicant: Amazon Technologies, Inc.
Inventor: Mohamed Mansour , Guangdong Pan
Abstract: Techniques for simulating a microphone array and generating synthetic audio data to analyze the microphone array geometry. This reduces the development cost of new microphone arrays by enabling an evaluation of performance metrics (False Rejection Rate (FRR), Word Error Rate (WER), etc.) without building device hardware or collecting data. To generate the synthetic audio data, the system performs acoustic modeling to determine a room impulse response associated with a prototype device (e.g., potential microphone array) in a room. The acoustic modeling is based on two parameters—a device response (information about acoustics and geometry of the prototype device) and a room response (information about acoustics and geometry of the room). The device response can be simulated based on the microphone array geometry, and the room response can be determined using a specialized microphone and a plane wave decomposition algorithm.
-
公开(公告)号:US10986437B1
公开(公告)日:2021-04-20
申请号:US16014275
申请日:2018-06-21
Applicant: Amazon Technologies, Inc.
Inventor: Guangdong Pan , Chad Jackman , Wontak Kim
Abstract: A beamformer system isolates a desired direction of an audio signal received from a first microphone array disposed on a first plane of the system and a second microphone array disposed on a second plane of the system. A spatial covariance matrix (SCM) defines the spatial covariance between pairs of microphones. A diagonal of the SCM is varied based on the placement of the microphones; values corresponding to one microphone array are increased, and values corresponding to the other microphone array are decreased.
-
公开(公告)号:US11483646B1
公开(公告)日:2022-10-25
申请号:US15995994
申请日:2018-06-01
Applicant: Amazon Technologies, Inc.
Inventor: Guangdong Pan , Philip Ryan Hilmes , Robert Ayrapetian
Abstract: Techniques for improving beamforming using filter coefficient values corresponding to virtual microphones are described. A system may define “virtual” microphone positions and determine corresponding filter coefficient values. These filter coefficient values may be applied to input audio data captured by actual physical microphones, enabling the system to improve performance of beamforming and/or to reduce a number of physical microphones without degrading performance. Offline testing and simulations may be performed to identify the best combination of virtual microphones and/or filter coefficient values for a particular look-direction. For example, the simulations may identify that a first filter coefficient corresponding to a first virtual microphone and a first direction will be associated with a first physical microphone and the first direction. During run-time processing, a device may generate beamformed audio data for the first direction by applying the first filter coefficient to input audio data captured by the first physical microphone.
-
公开(公告)号:US10582299B1
公开(公告)日:2020-03-03
申请号:US16216599
申请日:2018-12-11
Applicant: Amazon Technologies, Inc.
Inventor: Mohamed Mansour , Guangdong Pan
Abstract: Techniques for simulating a microphone array and generating synthetic audio data to analyze the microphone array geometry. This reduces the development cost of new microphone arrays by enabling an evaluation of performance metrics (False Rejection Rate (FRR), Word Error Rate (WER), etc.) without building device hardware or collecting data. To generate the synthetic audio data, the system performs acoustic modeling to determine a room impulse response associated with a prototype device (e.g., potential microphone array) in a room. The acoustic modeling is based on two parameters—a device response (information about acoustics and geometry of the prototype device) and a room response (information about acoustics and geometry of the room). The device response can be simulated based on the microphone array geometry, and the room response can be determined using a specialized microphone and a plane wave decomposition algorithm.
-
-
-