Methods, systems, and apparatus, including computer programs encoded on computer storage media for generating echo recordings. The system receives, by an autoencoder, an audio signal representation that represents an audio signal and a target echo embedding that comprises information about a target room. The autoencoder comprises an encoder and a decoder. The system generates, by the encoder, a content embedding and an estimated echo embedding. The system generates, by the decoder, an echo recording representation based on the content embedding and the target echo embedding.

A method for processing an audio signal in accordance with a room impulse response is described. The audio signal is processed with an early part of the room impulse response separate from a late reverberation of the room impulse response, wherein the processing of the late reverberation has generating a scaled reverberated signal, the scaling being dependent on the audio signal. The processed early part of the audio signal and the scaled reverberated signal are combined.

There is provided a system for generating instructions for adjustment of vehicle sub-system(s) according to an analysis of a computed six degrees of freedom (6 DOF) of vehicle occupant(s), comprising: hardware processor(s), and a non-transitory memory having stored thereon a code for execution by the at least one hardware processor, the code comprising instructions for: obtaining at least one image of a cabin of a vehicle captured by an image sensor, obtaining depth data from a depth sensor that senses the cabin of the vehicle, wherein the at least one image and the depth data depict at least one head of at least one occupant, computing 6 DOF for the at least one head according to the at least one image and depth data, and generating instructions for adjustment of at least one vehicle sub-system according to the computed 6 DOF of the at least one vehicle occupant.

In some examples, an apparatus comprises: a housing; an internal speaker housed within the housing; an internal microphone housed within the housing; an interface; and a controller configured to: receive, using the internal microphone, ingress audio signals; output, using the internal speaker, first egress audio signals at a first power level when the internal microphone receives the ingress audio signals; detect that an external speaker is connected to the interface; based on detecting that the external speaker is connected to the interface, disable the internal microphone; and output, using the external speaker, second egress audio signals when the internal microphone receives the ingress audio signals, the second egress audio signals being output at a second power level higher than the first power level.

The implementation of modal processors, which involve the parallel combination resonant filters, may be costly for applications such as artificial reverberation that can require thousands of modes. In one embodiment, the input signal is decomposed into a plurality of subbands, the outputs of which are downsampled. In each downsampled band, resonant filters are applied at the downsampled sampling rate, and their output is upsampled and filtered to form the band output. In these and other embodiments, a feature of responses of the mode filters have been optimized to minimize an aspect of a residual error after a point in time.

An apparatus and method of loudspeaker equalization. The method combines default tunings (generated based on a default listening environment) and room tunings (generated based on an end user listening environment) to result in combined tunings that account for differences between the end user listening environment and the default listening environment.

A system for determining the impulse response of an environment, the system comprising an audio emitting unit operable to emit a predetermined sound in the environment, an audio detection unit operable to record the sound output by the audio emitting unit, and an impulse response generation unit operable to identify an impulse response of the environment in dependence upon a frequency response of the audio emitting unit and/or the audio detection unit, and a difference between the predetermined sound and the recorded sound.

Playback of an audio signal is simulated from a playback position to a listening position. The simulation is performed with respect to a model of a listening area. The resulting loudness of the audio, perceived at the listening position, is rendered to a display. Other aspects are described and claimed.

Systems and methods for providing spatial audio are disclosed herein. In one example, the method includes receiving a first position of a first playback device relative to a user in a listening environment; receiving a second position of a second playback device relative to the user in the listening environment; transmitting, to a media content provider, location data corresponding to the first and second positions; receiving, from the media content provider, virtual media audio content associated with a virtual environment, the virtual media audio content comprising first and second audio signals generated based on the transmitted location data, wherein the generated first and second audio signals include one or more audio cues configured to enable the user to spatially perceive a location of a virtual object within the listening environment; and playing back the first audio signal via the first playback device in synchrony with playing back the second audio signal via the second playback device.

A system that performs early reflections filtering to suppress early reflections and improve sound source localization (SSL). During music playback and/or when a device is placed in a corner, acoustic reflections from nearby surfaces get boosted due to constructive interference, negatively impacting SSL and other processing of the device. To suppress these early reflections, the device uses an Early Reflections Filter (ERF) that makes use of Linear Prediction Coding (LPC), which is already being performed during speech processing. For example, the device generates raw audio signals using multi-channel LPC coefficients and then uses single-channel LPC coefficients for each raw audio signal in order to generate a filter that estimates the reflections. The device then uses this filter to suppress the early reflections and generate filtered audio signals, thus resulting in better audio processing and better overall device performance.