Abstract: An audio session management method may involve: determining, by an audio session manager, one or more first media engine capabilities of a first media engine of a first smart audio device, the first media engine being configured for managing one or more audio media streams received by the first smart audio device and for performing first smart audio device signal processing for the one or more audio media streams according to a first media engine sample clock; receiving, by the audio session manager and via a first application communication link, first application control signals from the first application; and controlling the first smart audio device according to the first media engine capabilities, by the audio session manager, via first audio session management control signals transmitted to the first smart audio device via a first smart audio device communication link and without reference to the first media engine sample clock.

Abstract: An attenuation or “gap” may be inserted into at least a first frequency range of at least first and second audio playback signals of a content stream during at least a first time interval to generate at least first and second modified audio playback signals. Corresponding audio device playback sound may be provided by at least first and second audio devices. At least one microphone may detect at least the first audio device playback sound and the second audio device playback sound and may generate corresponding microphone signals. Audio data may be extracted from the microphone signals in at least the first frequency range, to produce extracted audio data. A far-field audio environment impulse response and/or audio environment noise may be estimated based, at least in part, on the extracted audio data.

Abstract: Some methods may involve receiving a first content stream that includes first audio signals, rendering the first audio signals to produce first audio playback signals, generating first direct sequence spread spectrum (DSSS) signals, generating first modified audio playback signals by inserting the first DSSS signals into the first audio playback signals, and causing a loudspeaker system to play back the first modified audio playback signals, to generate first audio device playback sound. The method(s) may involve receiving microphone signals corresponding to at least the first audio device playback sound and to second through Nth audio device playback sound corresponding to second through Nth modified audio playback signals (including second through Nth DSSS signals) played back by second through Nth audio devices, extracting second through Nth DSSS signals from the microphone signals and estimating at least one acoustic scene metric based, at least partly, on the second through Nth DSSS signals.

Abstract: Some methods may involve receiving a first content stream that includes first audio signals, rendering the first audio signals to produce first audio playback signals, generating first direct sequence spread spectrum (DSSS) signals, generating first modified audio playback signals by inserting the first DSSS signals into the first audio playback signals, and causing a loudspeaker system to play back the first modified audio playback signals, to generate first audio device playback sound. The method(s) may involve receiving microphone signals corresponding to at least the first audio device playback sound and to second through Nth audio device playback sound corresponding to second through Nth modified audio playback signals (including second through Nth DSSS signals) played back by second through Nth audio devices, extracting second through Nth DSSS signals from the microphone signals and estimating at least one acoustic scene metric based, at least partly, on the second through Nth DSSS signals.

Abstract: The present disclosure relates to methods and apparatus for processing media content having video content and associated audio content. A method of processing media content having video content and associated audio content comprises the method includes receiving the video content and the associated audio content, analyzing the associated audio content, determining one or more navigation points for enabling navigation of the media content based on the analysis, wherein the one or more navigation points indicate points of interest in the associated audio content for short-term rewinding and/or fast forwarding, embedding the one or more navigation points into metadata for the media content, and outputting the video content, the associated audio content, and the metadata.

Abstract: Some implementations involve receiving, from a first subband domain acoustic echo canceller (AEC) of a first audio device in an audio environment, first adaptive filter management data from each of a plurality of first adaptive filter management modules, each first adaptive filter management module corresponding to a subband of the first subband domain AEC, each first adaptive filter management module being configured to control a first plurality of adaptive filters. The first plurality of adaptive filters may include at least a first adaptive filter type and a second adaptive filter type. Some implementations involve extracting, from the first adaptive filter management data, a first plurality of extracted features corresponding to a plurality of subbands of the first subband domain AEC and estimating a current local acoustic state based, at least in part, on the first plurality of extracted features.

Abstract: An audio processing method may involve receiving output signals from each microphone of a plurality of microphones in an audio environment, the output signals corresponding to a current utterance of a person and determining, based on the output signals, one or more aspects of context information relating to the person, including an estimated current proximity of the person to one or more microphone locations. The method may involve selecting two or more loudspeaker-equipped audio devices based, at least in part, on the one or more aspects of the context information, determining one or more types of audio processing changes to apply to audio data being rendered to loudspeaker feed signals for the audio devices and causing one or more types of audio processing changes to be applied. In some examples, the audio processing changes have the effect of increasing a speech to echo ratio at one or more microphones.

Abstract: An audio session management method may involve: determining, by an audio session manager, one or more first media engine capabilities of a first media engine of a first smart audio device, the first media engine being configured for managing one or more audio media streams received by the first smart audio device and for performing first smart audio device signal processing for the one or more audio media streams according to a first media engine sample clock; receiving, by the audio session manager and via a first application communication link, first application control signals from the first application; and controlling the first smart audio device according to the first media engine capabilities, by the audio session manager, via first audio session management control signals transmitted to the first smart audio device via a first smart audio device communication link and without reference to the first media engine sample clock.

Abstract: A noise estimation method including steps of generating gap confidence values in response to microphone output and playback signals, and using the gap confidence values to generate an estimate of background noise in a playback environment. Each gap confidence value is indicative of confidence of presence of a gap at a corresponding time in the playback signal, and may be a combination of candidate noise estimates weighted by the gap confidence values. Generation of the candidate noise estimates may but need not include performance of echo cancellation. Optionally, noise compensation is performed on an audio input signal using the generated background noise estimate. Other aspects are systems configured to perform any embodiment of the noise estimation method.

Abstract: An audio session management method for an audio environment having multiple audio devices may involve receiving, from a first device implementing a first application and by a device implementing an audio session manager, a first route initiation request to initiate a first route for a first audio session. The first route initiation request may indicate a first audio source and a first audio environment destination. The first audio environment destination may correspond with at least a first person in the audio environment, but in some instances will not indicate an audio device. The method may involve establishing a first route corresponding to the first route initiation request. Establishing the first route may involve determining a first location of at least the first person in the audio environment, determining at least one audio device for a first stage of the first audio session and initiating or scheduling the first audio session.

Abstract: A method may involve receiving output signals from each microphone of a plurality of microphones in the environment, each of the plurality of microphones residing in a microphone location of the environment, the output signals corresponding to an utterance of a person. The method may involve determining, based at least in part on the output signals, a zone within the environment that has at least a threshold probability of including the person's location and generating a plurality of spatially-varying attentiveness signals within the zone. Each attentiveness signal may be generated by a device located within the zone. Each attentiveness signal may indicate that a corresponding device is in an operating mode in which the corresponding device is awaiting a command and may indicate a relevance metric of the corresponding device.

Abstract: A noise estimation method including steps of generating gap confidence values in response to microphone output and playback signals, and using the gap confidence values to generate an estimate of background noise in a playback environment. Each gap confidence value is indicative of confidence of presence of a gap at a corresponding time in the playback signal, and may be a combination of candidate noise estimates weighted by the gap confidence values. Generation of the candidate noise estimates may but need not include performance of echo cancellation. Optionally, noise compensation is performed on an audio input signal using the generated background noise estimate. Other aspects are systems configured to perform any embodiment of the noise estimation method.

Abstract: A noise estimation method including steps of generating gap confidence values in response to microphone output and playback signals, and using the gap confidence values to generate an estimate of background noise in a playback environment. Each gap confidence value is indicative of confidence of presence of a gap at a corresponding time in the playback signal, and may be a combination of candidate noise estimates weighted by the gap confidence values. Generation of the candidate noise estimates may but need not include performance of echo cancellation. Optionally, noise compensation is performed on an audio input signal using the generated background noise estimate. Other aspects are systems configured to perform any embodiment of the noise estimation method.

Abstract: A pervasive listening method including steps of inserting at least one forced gap in a playback signal (thus generating a modified playback signal), and during playback of the modified playback signal, monitoring non-playback content (e.g., including by generating an estimate of background noise) in a playback environment using output of a microphone in the playback environment. Optionally, the method includes generation of the playback signal, including by processing of (e.g., performing noise compensation on) an input signal using a result (e.g., a background noise estimate) of the monitoring of non-playback content. Other aspects are systems configured to perform any embodiment of the pervasive listening method.

Abstract: A pervasive listening method including steps of inserting at least one forced gap in a playback signal (thus generating a modified playback signal), and during playback of the modified playback signal, monitoring non-playback content (e.g., including by generating an estimate of background noise) in a playback environment using output of a microphone in the playback environment. Optionally, the method includes generation of the playback signal, including by processing of (e.g., performing noise compensation on) an input signal using a result (e.g., a background noise estimate) of the monitoring of non-playback content. Other aspects are systems configured to perform any embodiment of the pervasive listening method.

Abstract: A noise estimation method including steps of generating gap confidence values in response to microphone output and playback signals, and using the gap confidence values to generate an estimate of background noise in a playback environment. Each gap confidence value is indicative of confidence of presence of a gap at a corresponding time in the playback signal, and may be a combination of candidate noise estimates weighted by the gap confidence values. Generation of the candidate noise estimates may but need not include performance of echo cancellation. Optionally, noise compensation is performed on an audio input signal using the generated background noise estimate. Other aspects are systems configured to perform any embodiment of the noise estimation method.

Abstract: In some embodiments, methods and systems for training an acoustic model, where the training includes a training loop (including at least one epoch) following a data preparation phase. During the training loop, training data are augmented to generate augmented training data. During each epoch of the training loop, at least some of the augmented training data is used to train the model. The augmented training data used during each epoch may be generated by differently augmenting (e.g., augmenting using a different set of augmentation parameters) at least some of the training data. In some embodiments, the augmentation is performed in the frequency domain, with the training data organized into frequency bands. The acoustic model may be of a type employed (when trained) to perform speech analytics (e.g., wakeword detection, voice activity detection, speech recognition, or speaker recognition) and/or noise suppression.

Abstract: The present disclosure relates to methods and apparatus for processing media content having video content and associated audio content. A method of processing media content having video content and associated audio content comprises the method includes receiving the video content and the associated audio content, analyzing the associated audio content, determining one or more navigation points for enabling navigation of the media content based on the analysis, wherein the one or more navigation points indicate points of interest in the associated audio content for short-term rewinding and/or fast forwarding, embedding the one or more navigation points into metadata for the media content, and outputting the video content, the associated audio content, and the metadata.