Systems and methods for suppressing noise and detecting voice input in a multi-channel audio signal captured by a plurality of microphones include (i) capturing a first audio signal via a first microphone and a second audio signal via a second microphone, wherein the first and second audio signals respectively comprises first and second noise content from a noise source; (ii) identifying the first noise content in the first audio signal; (iii) using the identified first noise content to determine an estimated noise content captured by the plurality of microphones; (iv) using the estimated noise content to suppress the first and second noise content in the first and second audio signals; (v) combining the suppressed first and second audio signals into a third audio signal; and (vi) determining that the third audio signal includes a voice input comprising a wake word.

The amount of far-field noise transmitted by a primary communication device in an open-plan office environment is reduced by defining an acoustic perimeter of reference microphones around the primary device. Reference microphones generate a reference audio input including far-field noise in the proximity of the primary device. The primary device generates a main audio input including the voice of the primary speaker as well as background noise. Reference audio input is compared to main audio input to identify the background noise portion of the main audio signal. A noise reduction algorithm suppresses the identified background noise in the main audio signal. The one or more reference microphones defining the acoustic perimeter may be included in separate microphone devices placed in proximity to the main desktop phone, microphones within other nearby desktop telephone devices, or a combination of both types of devices.

Systems and methods for optimizing voice detection via a network microphone device (NMD) based on a selected voice-assistant service (VAS) are disclosed herein. In one example, the NMD detects sound via individual microphones and selects a first VAS to communicate with the NMD. The NMD produces a first sound-data stream based on the detected sound using a spatial processor in a first configuration. Once the NMD determines that a second VAS is to be selected over the first VAS, the spatial processor assumes a second configuration for producing a second sound-data stream based on the detected sound. The second sound-data stream is then transmitted to one or more remote computing devices associated with the second VAS.

A method, and system, of digital room correction for a device, such as a smart speaker, including a loudspeaker. The method comprises capturing audio from an environment local to the device, for example from one or more microphones of a smart speaker. The captured audio is then processed to recognize one or more categories of sound. A digital room correction procedure may then be controlled dependent upon recognition and/or analysis of at least one of the categories of sound.

Described herein is an audio device with a microphone which may adapt the audio output volume of a speaker by either increasing or decreasing output volume based on an audio input volume from a user and a distance from the user to the audio device. The audio device may also adapt its output volume to lower the audio output based on detecting one or more interruptions including occupancy and acoustic sounds.

Examples described herein involve configuring a playback device based on distortion, such as that caused by a barrier. One implementation may involve causing the playback device to play audio content according to an existing playback configuration, determining an existing frequency response of the playback device in a given system, and determining whether a difference between the existing frequency response of the playback device in the given system and a predetermined frequency response for the playback device is greater than a predetermined distortion threshold. If it is determined that the difference between the existing frequency response of the playback device and the predetermined frequency response for the playback device is greater than the predetermined distortion threshold, then the existing playback configuration of the playback device is changed to an updated playback configuration of the playback device and the playback device plays audio content according to the updated playback configuration.

An example method of operation may include determining a frequency response to a measured chirp signal detected from one or more speakers, determining an average value of the frequency response based on a high limit value and a low limit value, subtracting a measured response from a target response, and the target response is based on one or more filter frequencies; determining a frequency limited target filter with audible parameters based on the subtraction, and applying an infinite impulse response (IIR) biquad filter based on an area defined by the frequency limited target filter to equalize the frequency response of the one or more speakers.

Example techniques facilitate calibration of a playback device. An example implementation involves a computing device capturing, via a microphone, data representing multiple iterations of a calibration sound as played by a playback device. The computing device identifies multiple sections within the captured data. Two or more sections represent respective iterations of the calibration sound as played by the playback device. Based on the multiple identified sections, the computing device determines a frequency response of the playback device, the frequency response of the playback device representing audio output by the playback device and acoustic characteristics of an environment around the playback device. Based on the frequency response of the playback device and a target frequency response, the computing device determines one or more parameters of an audio processing algorithm and sends, to the playback device, the one or more parameters of the audio processing algorithm.

A premises security system for providing audio simulating occupancy of a premises. The system includes a video doorbell having a presence sensor and a security hub component communicatively coupled with the video doorbell. The security hub component includes a microphone for capturing sound within the premises, at least one speaker positioned within the premises, an audio driver for driving the speaker, a storage device, and a processor coupled to the microphone, the storage device, and the audio driver. The processor executes machine-readable instructions that control the processor to: capture, using the microphone, audio content of sounds within the premises; store the audio content in the storage device; and control the audio driver to play the audio content through the speaker in response to receiving an indication of the presence of a visitor from the video doorbell.

The amount of far-field noise transmitted by a primary communication device in an open-plan office environment is reduced by defining an acoustic perimeter of reference microphones around the primary device. Reference microphones generate a reference audio input including far-field noise in the proximity of the primary device. The primary device generates a main audio input including the voice of the primary speaker as well as background noise. Reference audio input is compared to main audio input to identify the background noise portion of the main audio signal. A noise reduction algorithm suppresses the identified background noise in the main audio signal. The one or more reference microphones defining the acoustic perimeter may be included in separate microphone devices placed in proximity to the main desktop phone, microphones within other nearby desktop telephone devices, or a combination of both types of devices.