Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.

An audio notification system for an autonomous vehicle (AV) determines that the AV is within range of a user and emits a sound though a speaker of the AV to notify that the user that the vehicle has arrived. The audio notification system may include a sensor for sensing that the user has accessed the AV, and turns off the sound in response to the user accessing the AV. The audio notification may be generated according to one or more audio options, e.g., volume, pitch, or audio pattern.

A backrest for a vehicle seat may have a backrest part, a head restraint part and an acoustic arrangement. The acoustic arrangement is arranged above the backrest part and may have at least one central loudspeaker and at least two side loudspeakers. The central loudspeaker may be built into the head restraint part and each of the at least two side loudspeakers may be arranged on a support. A vehicle seat with the backrest is also provided.

A class D amplifier circuit receives an analog audio signal with a first reference voltage as its center level, and outputs an output pulse signal having a duty cycle that corresponds to the analog audio signal. A bias circuit generates a second reference voltage having a voltage level obtained as a division of the first reference voltage and the power supply voltage. A periodic voltage generating circuit of the class D amplifier circuit generates a periodic voltage having a triangle waveform or otherwise a sawtooth waveform having an amplitude that corresponds to the second reference voltage.

Motor vehicle with sound system A motor vehicle (10) defining a longitudinal axis (X), a front side, and a median (P) plane including the longitudinal axis (X) and which is vertical, and comprising: a structure (14) comprising a bulkhead (34), at least one front seat (26A) for a driver, and a floor covering (18), the bulkhead and the floor covering partially delimiting a passenger compartment (35), and a sound system (12) including at least one speaker enclosure (42) rigidly attached to the structure, the speaker enclosure comprising at least one woofer (50A) and being located close to the median plane (P): either longitudinally between the bulkhead and a front edge of the front seat, or longitudinally astride a front zone (40A) of the passenger compartment intended to receive the driver and a rear zone (40B) of the passenger compartment intended to receive one or more rear passengers of the motor vehicle.

An audio communication system for communication between vehicle occupants in a vehicle, including an image capturing device configured to monitor a first vehicle occupant, a processor configured to receive an image of the first vehicle occupant from the image capturing device and determine whether the first vehicle occupant is attracting attention from a second vehicle occupant, a first microphone associated to the first vehicle occupant configured to receive an audio input from the first vehicle occupant in response to the determination of the first vehicle occupant attracting the second vehicle occupant's attention, and a first speaker associated to the second vehicle occupant configured to activate an audio augmentation of the received audio input in the first speaker and output the augmented audio input.

A system for controlling an electric machine of a vehicle includes, among other things, a controller module configured to attenuate noise from the electric machine by altering a corrective voltage in response to feedback about the noise. The corrective voltage and a fundamental voltage command are supplied to the electric machine as a combined voltage command. The corrective voltage is on a harmonic adjacent to a harmonic of the noise. A method of controlling noise associated with an electric machine of a vehicle includes, among other things, altering a corrective voltage to attenuate noise in response to feedback about the noise. The corrective voltage and a fundamental voltage command are supplied to the electric machine as a combined voltage command. The corrective voltage is on a harmonic adjacent to a harmonic of the noise.

An ambient sound environment is captured by a microphone array of an autonomous vehicle traveling in the ambient sound environment. A perception module of the autonomous vehicle classifies sounds and localizes sound sources in the ambient sound environment. Classification is performed using spectrum analysis and/or machine learning. In an embodiment, sound sources within a field of view (FOV) of an image sensor of the autonomous vehicle are localized in a visual scene generated by the perception module. In an embodiment, one or more sound sources outside the FOV of the image sensors are localized in a static digital map. Localization is performed using parametric or non-parametric techniques and/or machine learning. The output of the perception module is input into a planning module of the autonomous vehicle to plan a route or trajectory for the autonomous vehicle in the ambient sound environment.

An integration unit IU for tuning an OEM sound system augmented with aftermarket components, such as an amplifier or a subwoofer. The integration unit is contained in a small housing that can be installed inconspicuously in most vehicles without removing the original head unit. The unit may comprise a DSP-based active line output converter that is configured to automatically detect the frequency response and phase of the OEM head unit. The unit performs various algorithms to detect and analyze crossovers, EQ, time delay, and allpass filters and then matches left and right audio channels. The IU may allow for low bass correction detecting and defeating the factory high pass filter. Still further, the IU can correct the various filters to ensure a clean, uncolored audio signal for the augmented components.

An audio processing method for an audio system for a seat headrest, the audio system having at least two loudspeakers positioned on either side of the headrest and an audio processing module designed to apply at least one audio processing operation. The method includes the steps of: acquiring images of the head of a user of the audio system using an image acquisition device; processing the acquired images in order to determine, within a predetermined three-dimensional spatial reference frame, a spatial position of each ear of the user; and, on the basis of said determined spatial positions of the ears of the user and based on calibration information previously recorded in connection with an audio processing operation, determining calibration information for adapting the audio processing operation to the determined spatial positions of the ears of the user. Also included is an associated audio system for a seat headrest.