A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.

A method for hybrid noise suppression involves receiving a first processed audio signal and a second processed audio signal from an audio device. The first processed audio signal results from a comprehensive audio processing including a noise spectrum estimate-based noise suppression performed on a noisy audio input signal obtained by the audio device. The second processed signal results from a partial audio processing excluding the noise spectrum estimate-based noise suppression performed on the noisy audio input signal. The method further involves temporally aligning the second processed audio signal with the first processed audio signal, predicting a noise suppression parameter using a neural network model operating on the second processed audio signal after the temporal alignment, generating a noise-suppressed audio output signal from the first processed audio signal after the temporal alignment using the noise suppression parameter, and outputting the noise-suppressed audio output signal.

In at least one embodiment, an embedded Linux system is provided. The Linux system includes a memory, a system on a chip (SoC) device, and a first circuit. The SoC device includes the memory and is programmed to process at least a reference signal indicative of undesired audio content and a measured signal indicative of measured audio data in a listening environment. The first circuit is programmed to receive the reference signal and the measured signal. The first circuit is further programmed to merge the reference signal with the measured signal to provide a combined system input to the SoC device to prevent temporal misalignment between the reference signal and the measured signal caused by one or more software layers of the Linux system.

A steerable speaker array is provided, comprising a plurality of drivers arranged in a concentric, nested configuration formed by arranging the drivers in a plurality of concentric groups and placing the groups at different radial distances from a central point of the configuration. Each group is formed by a subset of the plurality of drivers being positioned at predetermined intervals from each other along a perimeter of the group. Also, the concentric groups are harmonically nested and rotationally offset from each other. An audio system is also provided comprising at least one steerable speaker array and a beamforming system configured to receive one or more input audio signals from an audio source, generate a separate audio output signal for each driver of the speaker array based on at least one of the input signals, and provide the audio output signals to the corresponding drivers to produce a beamformed audio output.

A method of echo path delay destination and echo cancellation is described in this disclosure. The method includes: obtaining a reference signal, a microphone signal, and a trained multi-task deep neural network, wherein the multi-task deep neural network comprises a first neural network and a second neural network; generating, using the first neural network of the multi-task deep neural network, an estimated echo path delay based on the reference signal and the microphone signal; updating the reference signal based on the estimated echo path delay; and generating, using the second neural network of the multi-task deep neural network, an enhanced microphone signal based on the microphone signal and the updated reference signal.

An illustrative controller includes: a transmitter to drive the acoustic transducer to generate acoustic bursts; a receiver to sense a response of the acoustic transducer to echoes; and a processing circuit coupled to the transmitter and to the receiver, the processing circuit configured to convert said received response into output data by: correlating said response to a driving signal to obtain a correlation response; distinguishing peak areas from non-peak areas in said correlation response; deriving a noise level in a portion of said correlation response based on the non-peak areas within said portion; calculating a signal to noise ratio (SNR) for a peak signal within the portion as a ratio of a peak value for the peak signal to the noise level in said portion of said correlation response; and accepting the peak signal as an echo only if the SNR for said peak signal exceeds a predetermined threshold.

A method for hybrid noise suppression involves receiving a first processed audio signal and a second processed audio signal from an audio device. The first processed audio signal results from a comprehensive audio processing including a noise spectrum estimate-based noise suppression performed on a noisy audio input signal obtained by the audio device. The second processed signal results from a partial audio processing excluding the noise spectrum estimate-based noise suppression performed on the noisy audio input signal. The method further involves temporally aligning the second processed audio signal with the first processed audio signal, predicting a noise suppression parameter using a neural network model operating on the second processed audio signal after the temporal alignment, generating a noise-suppressed audio output signal from the first processed audio signal after the temporal alignment using the noise suppression parameter, and outputting the noise-suppressed audio output signal.

In some implementations, an output of a first channel of an echo cancellation variable filter having an output of a first microphone output from a second speaker as an input is added to an output of a second microphone. An echo cancellation coefficient updating unit updates the filter coefficient of the first channel so that the error that is the output of a second adder is minimized. Using the output of the second channel that uses the output of a sound source device output from the first speaker as an input and shares the filter coefficient with the first channel as a reference signal, and the output of the second microphone as an error, the noise cancellation coefficient updating unit updates the filter coefficient of the noise cancellation variable filter that generates a noise-canceling sound to be output from the output of the sound source device to the second speaker.

Example techniques involve noise-robust acoustic echo cancellation. An example implementation may involve causing one or more speakers of the playback device to play back audio content and while the audio content is playing back, capturing, via the one or more microphones, audio within an acoustic environment that includes the audio playback. The example implementation may involve determining measured and reference signals in the STFT domain. During each n.sup.th iteration of an acoustic echo canceller (AEC): the implementation may involve determining a frame of an output signal by generating a frame of a model signal by passing a frame of the reference signal through an instance of an adaptive filter and then redacting the n.sup.th frame of the model signal from an n.sup.th frame of the measured signal. The implementation may further involve determining an instance of the adaptive filter for a next iteration of the AEC.

Systems and methods for audio listening devices, comprise a speaker coupled to a first housing, a sound port having a first end and a second end, wherein the first end is coupled to the first housing, and the second end is configured to be inserted in an ear canal of a person such that sound waves emitted from the speaker propagates via a secondary path to the ear canal through the sound port, active noise cancellation (ANC) components configured to generate anti-noise signals through the micro-speakers to cancel external noise, and a first microphone disposed within the sound port at the second end of the sound port such that the first microphone is configured to detect the anti-noise signal that propagates through the sound port via the secondary path and the external noise that propagates via a primary path.