Abstract: Processes, methods, systems, and devices are disclosed for intelligently detecting speech or in audio signals and smoothly transitioning to mode that enables a user to better understand the speech. For example, aspects of the present disclosure provide method for processing and producing audio signals. During playback of an audio signal, the method analyzes content of the audio signal prior to the playback of the content to determine whether one or more predefined conditions are met to indicate that the content includes speech. In response to determining the one or more predefined conditions are met, the method automatically applies to the audio signal a first playback equalization configured to enhance the speech within the content. In response to determining the one or more predefined conditions are not met, the method comprises applying to the audio signal no playback equalization or a second playback equalization different from the first playback equalization.

Abstract: Aspects of the present disclosure provide techniques, including devices and system implementing the techniques, to provide feedback to a user of an event when the user is wearing a wearable device. For example, the wearable device may provide high quality noise canceling audio playback to the user, lowering the user's situation awareness. The techniques include measuring ambient sound using two or more microphones on the wearable device. The event is determined based on the measured ambient sound. A location attribute of the event is determined. A deep learning algorithm may be used to identify the nature and/or classification of the event and rule out events that the user prefers to ignore. Upon determining the event that merits the user's attention, the user is provided feedback of the determined event and the location attribute, the feedback indicating the nature and location of the event.

Abstract: Aspects of the present disclosure provide techniques, including devices and system implementing the techniques, to provide feedback to a user of an event when the user is wearing a wearable device. For example, the wearable device may provide high quality noise canceling audio playback to the user, lowering the user's situation awareness. The techniques include measuring ambient sound using two or more microphones on the wearable device. The event is determined based on the measured ambient sound. A location attribute of the event is determined. A deep learning algorithm may be used to identify the nature and/or classification of the event and rule out events that the user prefers to ignore. Upon determining the event that merits the user's attention, the user is provided feedback of the determined event and the location attribute, the feedback indicating the nature and location of the event.

Abstract: Various implementations include approaches for controlling a wearable audio device. Particular approaches include: receiving data indicating the wearable audio device is proximate an additional wearable audio device worn by an additional user and running a personally attributed audio engine; and initiating personally attributed audio playback at the wearable audio device, where the personally attributed audio playback includes audio playback associated with the additional user.

Abstract: Various implementations include approaches for controlling a wearable audio device. Particular approaches include: receiving data indicating the wearable audio device is proximate an additional wearable audio device worn by an additional user and running a personally attributed audio engine; and initiating personally attributed audio playback at the wearable audio device, where the personally attributed audio playback includes audio playback associated with the additional user.

Abstract: Various aspects include approaches for intelligent acoustic beam steering. In particular aspects, a computer-implemented method of controlling a microphone array includes: generating an acoustic map including an acoustic description of a physical environment proximate the speaker system; focusing the microphone array in a direction based upon the acoustic map prior to receiving a voice command input at the microphone array, where generating the acoustic map includes: detecting a location of at least one noise source in the physical environment; and creating a microphone array filter configured to at least partially reject the at least one noise source; receiving voice feedback input from a user at the microphone array; and updating the acoustic map of the physical environment based upon the received voice feedback input.

Abstract: Various aspects include approaches for intelligent acoustic beam steering. In particular aspects, a computer-implemented method of controlling a microphone array includes: generating an acoustic map including an acoustic description of a physical environment proximate the speaker system; focusing the microphone array in a direction based upon the acoustic map prior to receiving a voice command input at the microphone array, where generating the acoustic map includes: detecting a location of at least one noise source in the physical environment; and creating a microphone array filter configured to at least partially reject the at least one noise source; receiving voice feedback input from a user at the microphone array; and updating the acoustic map of the physical environment based upon the received voice feedback input.

Abstract: Various aspects include approaches for intelligent acoustic beam steering. In some implementations, a method of controlling a microphone array in a speaker system is disclosed. In other implementations, a speaker system is disclosed. In particular aspects, a computer-implemented method of controlling a microphone array includes: generating an acoustic map including an acoustic description of a physical environment proximate the speaker system; and focusing the microphone array in a direction based upon the acoustic map prior to receiving a voice command input at the microphone array.

Abstract: Various aspects include approaches for intelligent acoustic beam steering. In some implementations, a method of controlling a microphone array in a speaker system is disclosed. In other implementations, a speaker system is disclosed. In particular aspects, a computer-implemented method of controlling a microphone array includes: generating an acoustic map including an acoustic description of a physical environment proximate the speaker system; and focusing the microphone array in a direction based upon the acoustic map prior to receiving a voice command input at the microphone array.

Abstract: A development platform for developing a skill for a persistent companion device (PCD) includes an asset development library having an application programming interface (API) configured to enable a developer to at least one of find, create, edit and access one or more content assets utilizable for creating a skill, an expression tool suite having one or more APIs via which are received one or more expressions associated with the skill as specified by the developer wherein the skill is executable by the PCD in response to at least one defined input, a behavior editor for specifying one or more behavioral sequences of the PCD for the skill and a skill deployment facility having an API for deploying the skill to an execution engine of the PCD.