Amazon Technologies, Inc.

Pradeep Kumar Govindaraju

Robert Ayrapetian

Amit Singh Chhetri

Rong Hu

Steven Sensarn

Savaskan Bulek

Mrudula V Athi

Gautam Shreedhar Bhat

A system that performs beam selection and beam merging using beam-specific signal quality metrics corresponding to a minimum noise floor. For example, a device may track a minimum noise floor for each beam, determine a highest minimum noise floor across the beams, and determine a noise floor ratio between the beam-specific minimum noise floor and the highest minimum noise floor. Using a combination of the noise floor ratio and signal-to-noise ratio (SNR) values, the device may perform beam selection by prioritizing low background noise as well as high SNR to select a pre-defined beam group. In addition, the device may use the noise floor ratio to perform beam merging and generate single-channel output audio data using the selected beam group. For example, the device may scale the beams based on a combination of the SNR value and the noise floor ratio.

Group beam selection and beam merging

A system configured to improve audio processing by performing dereverberation and noise reduction during a communication session. In some examples, the system may include a deep neural network (DNN) configured to perform speech enhancement, which is located after an Acoustic Echo Cancellation (AEC) component. For example, the DNN may process isolated audio data output by the AEC component to jointly mitigate additive noise and reverberation. In other examples, the system may include a DNN configured to perform acoustic interference cancellation, which may jointly mitigate additive noise, reverberation, and residual echo, removing the need to perform residual echo suppression processing. The DNN is configured to process complex-valued spectrograms corresponding to the isolated audio data and/or estimated echo data generated by the AEC component.

Dereverberation and noise reduction

Techniques for improving microphone noise suppression are provided. As wind noise may disproportionately impact a subset of microphones, a method for processing audio data using two adaptive reference algorithm (ARA) paths in parallel is provided. For example, first ARA processing performs noise cancellation using all microphones, while second ARA processing performs noise cancellation using only a portion of the microphones. As the first ARA processing and the second ARA processing are performed in parallel, beam merging can be performed using beams from the first ARA, the second ARA, and/or a combination of each. In addition, beam merging can be performed using beam sections instead of individual beams to further improve performance and reduce attenuation to speech.

Parallel noise suppression

A system configured to detect a tap event on a surface of a device using microphone audio data and motion data. Instead of using a physical sensor to detect the tap event, the device detects a tap event based on a power level difference between two or more microphones. When a power ratio exceeds a threshold, the device may detect a tap event and perform an action, such as delaying or ending an alarm. To reduce false positives caused by wind or loud noises close to the microphones, the device may confirm a tap event using motion data that indicates actual movement of the device. In some examples, the device may detect the tap event using a neural network processing the microphone data and the motion data. In addition, the device may embed the motion data within the microphone data using unused bits of the microphone data.

Growing community of inventors

San Jose, CA, United States of America

Pradeep Kumar Govindaraju