An audio system can be configured to generate an audio heatmap for the audio emission potential profiles for one or more speakers, in specific or arbitrary locations. The audio heatmap maybe based on speaker location and orientation, speaker acoustic properties, and optionally environmental properties. The audio heatmap often shows areas of low sound density when there are few speakers, and areas of high sound density when there are a lot of speakers. An audio system may be configured to normalize audio signals for a set of speakers that cooperatively emit sound to render an audio object in a defined audio object location. The audio signals for each speaker can be normalized to ensure accurate rendering of the audio object without volume spikes or dropout.

An audio system is provided that efficiently detects speaker arrays and configures the speaker arrays to output sound. In this system, a computing device may record the addresses and/or types of speaker arrays on a shared network while a camera captures video of a listening area, including the speaker arrays. The captured video may be analyzed to determine the location of the speaker arrays, one or more users, and/or the audio source in the listening area. While capturing the video, the speaker arrays may be driven to sequentially emit a series of test sounds into the listening area and a user may be prompted to select which speaker arrays in the captured video emitted each of the test sounds. Based on these inputs from the user, the computing device may determine an association between the speaker arrays on the shared network and the speaker arrays in the captured video.

An example computing system may be configured to receive an indication that a user device has been detected in a commercial environment and to determine a first set of musical preferences associated with the commercial environment. The example computing system may also be configured to determine a user profile associated with the user device and to determine a second set of musical preferences associated with the user profile. The example computing system may also be configured to, based on at least (i) the first set of musical preferences associated with the commercial environment, and (ii) the second set of musical preferences associated with the user profile, determine one or more media items for playback and then cause one or more playback devices in the commercial environment to play back the one or more media items.

An acoustic echo cancellation (AEC) system that detects and compensates for differences in sample rates between the AEC system and a set of wireless speakers based on a search-based trial-and-error technique. The system individually determines a frequency offset for each microphone-speaker pair using an iterative process, determining an echo-return loss enhancement (ERLE) value for each offset that is tried, and selecting the frequency offset associated with the largest ERLE value.

A system and method for driving a loudspeaker array across directivities and frequencies to maintain timbre constancy in a listening area is described. In one embodiment, a frequency independent room constant describing the listening area is determined using the directivity index of a first beam pattern, the direct-to-reverberant ratio DR at the listener's location in the listening area, and an estimated reverberation time T.sub.60 for the listening area at a designated frequency. On the basis of this room constant, an offset may be generated for a second beam pattern. The offset describes the decibel difference between first and second beam patterns to achieve constant timbre and may be used to adjust the second beam pattern at multiple frequencies. Maintaining constant timbre improves audio quality regardless of the characteristics of the listening area and the beam patterns used to represent sound program content. Other embodiments are also described.

A signal processing device includes a power estimating unit that treats the feature quantity of a signal including reverberation as the input; inputs an observation feature quantity corresponding to an observation signal to a neural network which is learnt in such a way that the estimate value of the feature quantity corresponding to the power of the signal having reduced reverberation, from among the input signal, is output; and estimates the estimate value of the feature quantity corresponding to the power of the signal having reduced reverberation and corresponding to the observation signal. Moreover, the signal processing device includes a regression coefficient estimating unit that uses the estimate value of the feature quantity corresponding to the power as obtained as the estimation result by the power estimating unit, and estimates a regression coefficient of the autoregressive process for generating the observation signal.

A sound signal processing method includes receiving a sound signal, generating an early reflection sound control signal that reproduces an early reflection sound and a reverberant sound control signal that reproduces a reverberant sound from the sound signal, controlling a volume of the sound signal and distributing the sound signal to generate a direct sound control signal, and mixing the direct sound control signal, the early reflection sound control signal that reproduces a direct sound, and the reverberant sound control signal to generate an output signal.

A method and system for improving the intelligibility of an audio signal emitted from plural audio output devices in a space can help mitigate systems that have low intelligibility at installation due to reverberation effects; it can provide a quick post installation check of a system prior to a full-fledged STIPA (Speech Transmission Index for Public Address Systems) or equivalent test; and it allows for a quick verification if changes to the acoustical environment are expected to have major effects on STIPA tests.

Systems and methods for calibrating a playback device include (i) outputting first audio content; (ii) capturing audio data representing reflections of the first audio content within a room in which the playback device is located; (iii) based on the captured audio data, determining an acoustic response of the room; (iv) connecting to a database comprising a plurality of sets of stored audio calibration settings, each set associated with a respective stored acoustic room response of a plurality of stored acoustic room responses; (v) querying the database for a stored acoustic room response that corresponds to the determined acoustic response of the room in which the playback device is located; and (vi) applying to the playback device a particular set of stored audio calibration settings associated with the stored acoustic room response that corresponds to the determined acoustic response of the room in which the playback device is located.

Example techniques may involve performing aspects of a spatial calibration. An example implementation may include detecting a trigger condition that initiates calibration of a media playback system including multiple audio drivers that form multiple sound axes, each sound axis corresponding to a respective channel of multi-channel audio content The implementation may also include causing the multiple audio drivers to emit calibration audio that is divided into constituent frames, the multiple sound axes emitting calibration audio during respective slots of each constituent frame. The implementation may further include recording the emitted calibration audio. The implementation may include causing delays for each sound axis of the multiple sound axes to be determined, the determined delay for each sound axis based on the slots of recorded calibration audio corresponding to the sound axes and causing the multiple sound axes to be calibrated.