Techniques for adaptive noise cancellation for multiple audio endpoints in a shared space are described. According to one example, a method includes detecting, by a first audio endpoint, one or more audio endpoints co-located with the first audio endpoint at a first location. A selected audio endpoint of the one or more audio endpoints is identified as a target noise source. The method includes obtaining, from the selected audio endpoint, a loudspeaker reference signal associated with a loudspeaker of the selected audio endpoint and removing the loudspeaker reference signal from a microphone signal associated with a microphone of the first audio endpoint. The method also includes providing the microphone signal from the first audio endpoint to at least one of a voice user interface (VUI) or a second audio endpoint, wherein the second audio endpoint is located remotely from the first location.

Systems and methods are provided for conducting conference calls using doppler-based, i.e., reverberation-based techniques. The embodiments comprise a call device performing operations to join a call session hosted on a session server; receive sensor data comprising an audio signal from a first microphone and location information associated with the first microphone; determine a reverberation parameter associated with the location information; generate a first processed audio signal based on the audio signal and the reverberation parameter; and transmit the first processed audio signal to the session server. The session server may perform operations to receive a respective processed audio signal; determine a sound quality parameter of the respective processed audio signal; generate a balanced audio signal based on the sound quality parameter and the received processed audio signal; and transmit the balanced audio signal to a remote call device belonging to a second party.

Method and system for maintaining accuracy of voice recognition are described herein. The audio system reproducing sound using a loudspeaker array that is housed in a loudspeaker cabinet may selection from a number of sound rendering modes and changing the selected sound rendering mode based on the current playback volume set on the audio system. The sound rendering modes include at least one of: a number of free space modes and a number of complex modes. Other aspects are also described and claimed.

A sound system for a vehicle includes a plurality of microphones to detect sounds emanating from outside of the vehicle. A sound processor is operable to process microphone output signals of the microphones to identify a source of at least some sounds detected by the microphones. The sound processor processes microphone output signals to identify a sound of interest outside of the vehicle, which includes at least one of (i) a siren of an emergency vehicle and (ii) a horn of another vehicle. Responsive to identification by the sound processor of the sound of interest, a plurality of speakers disposed in the cabin of the vehicle generate sound representative of the identified sound of interest. While the speakers are generating sound representative of the identified sound of interest, sounds generated by the speakers based on audio signals from other sound systems in the vehicle are diminished.

Systems and methods are provided for conducting conference calls using doppler-based, i.e., reverberation-based techniques. The embodiments comprise a call device performing operations to join a call session hosted on a session server; receive sensor data comprising an audio signal from a first microphone and location information associated with the first microphone; determine a reverberation parameter associated with the location information; generate a first processed audio signal based on the audio signal and the reverberation parameter; and transmit the first processed audio signal to the session server. The session server may perform operations to receive a respective processed audio signal; determine a sound quality parameter of the respective processed audio signal; generate a balanced audio signal based on the sound quality parameter and the received processed audio signal; and transmit the balanced audio signal to a remote call device belonging to a second party.

A sound collecting system includes a plurality of sound collecting units that collect sound and a sound collecting device. The plurality of sound collecting units send sound collection data including audio data and time data to the sound collecting device. The sound collecting device includes a processor that manages time for the plurality of sound collecting units and receives an instruction specifying a sound collecting location, and an output unit. The processor of the sound collecting device synthesizes the audio data of the plurality of sound collecting units on the basis of the time data of the plurality of sound collecting units, and outputs, from the output unit, the audio data of the sound collecting location.

A method, apparatus and computer program including: obtaining a spatial audio signal from a plurality of microphones; dividing the obtained spatial audio signal into at least a first component and a second component; applying a first audio signal optimizing system to the first component and applying a second audio signal optimizing system to the second component; and enabling a signal including the optimized components to be provided to a speaker for rendering.

A method of real-time noise reduction including generating spectral data using temporally localized spectral representations of a received audio signal, determining detection of voice by comparing first and second filtered data, and generating noise-reduced audio output by attenuating noise based on the determined detection of voice. The first and second filtered data are formed by attenuating temporal variations of the spectral data based on, respectively, a first timescale and a second timescale. A noise reduction system, comprising processing circuitry configured to execute a method of real-time noise reduction to generate an output that is transmitted via an output port of the noise reduction system. A noise-reduction microphone comprising a housing having a transducer coupled to a processor therein to execute a method of real-time noise reduction, and an output port. A non-transitory computer-readable medium having instructions to cause a processor to perform a method of real-time noise reduction.

Systems and methods for improved acoustic echo cancellation and convergence state detection are disclosed. An adaptive filter of a network microphone device (NMD) can be used to generate a filter output to be applied to microphone input signals for echo cancellation. The filter output can be generated using a reference signal corresponding to source audio content played back via transducers of the NMD. The adaptive filter can be updated dynamically over time based at least in part on an adaptation parameter that determines the rate of adaptation. In response to determining that a reset event has occurred, the adaptation parameter can be reset to a default value. Additionally or alternatively, in response to detecting a convergence error, the adaptation parameter can be reset to a default value.

An audio encoding device and an audio decoding device are described herein. The audio encoding device may examine a set of audio channels/channel groups representing a piece of sound program content and produce a set of ducking values to associate with one of the channels/channel groups. During playback of the piece of sound program content, the ducking values may be applied to all other channels/channel groups. Application of these ducking values may cause (1) the reduction in dynamic range of ducked channels/channel groups and/or (2) movement of channels/channel groups in the sound field. This ducking may improve intelligibility of audio in the non-ducked channel/channel group. For instance, a narration channel/channel group may be more clearly heard by listeners through the use of selective ducking of other channels/channel groups during playback.