Method, apparatus, and computer-readable media to manage undesired sound sources in microphone pickup/focus zones preferably mitigates one or more of the undesired sound source(s) in a space having a plurality of microphones and at least one desired sound source. Preferably, at least one microphone input receives plural microphone input signals from the plurality of microphones in the space. Preferably, the least one processor is coupled to the at least one microphone input and receives the plural microphone input signals. Preferably, the at least one processor determines plural micro-zones in the space. Preferably, the at least one processor determines a threshold sound field level for each micro-zone based on received plural microphone input signals that correspond to the one or more undesired sound source(s). Preferably, the at least one processor recognizes a desired sound source when received plural microphone input signals exceed one or more threshold sound field level.

A method of performing automatic speech recognition (ASR) using end-pointing markers generated using accelerometer-based voice activity detector starts with a voice activity detector (VAD) generating an accelerometer VAD output (VADa) based on data output by at least one accelerometer that is included in at least one earbud. The at least one accelerometer to detect vibration of the user's vocal chords. A voice processor detects a speech signal based on acoustic signals from at least one microphone. An end-pointer generates the end-pointing markers based on the VADa output and an ASR engine performs ASR on the speech signal based on the end-pointing markers. Other embodiments are also described.

System and techniques for a microphone board for far field automatic speech recognition are described herein. The microphone board may include a first plurality of microphones disposed along a circumference of a circle on a surface and a second plurality of microphones disposed along a line on the surface. First connections to the first plurality of microphones may be grouped together and second connections to the second plurality of microphones are grouped together. The first connections and the second connections may be provided to an external entity of the surface via a connector.

A rear panel of an electronic keyboard instrument has a frame portion including multiple sound radiation holes, and the frame portion has a first hole frame including a hole forming surface of the sound radiation hole and a second hole frame including a hole forming surface of the sound radiation hole which is longer in a thickness direction of the frame portion (a Y-axis direction) than the first frame.

A rear panel 15, which is an external member, includes a frame portion 110 including multiple sound radiation holes 150 including a first sound radiation hole 160-1 and a second sound radiation hole 160-2, a first sloping portion 160b disposed in the frame portion 110 with a first sloping surface 161a oriented in a first direction 161c, the sloping surface 161a being disposed within an area of the first sound radiation hole 160-1 in such a manner as to slope from a thickness direction (a Y-axis direction) of the frame portion 110, and a second sloping portion 162b disposed in the frame portion 110 with a sloping surface 162a oriented in a second direction 162c which differs from the first direction 161c, the sloping surface 162a being disposed within an area of the second sound radiation hole 160-2 in such a manner as to slope from the thickness direction (the Y-axis direction) of the frame portion 110.

Sound bars with improved sound distribution are disclosed having at least first and second speaker drivers. The sound bars can have a spatial deviation point between the at least first and second speaker drivers such that the first and second speaker drivers are facing different directions. A second spatial deviation point can also be included to create additional directions for the driver speakers to face. The sound bars can include both active and passive speaker drivers.

A loudspeaker baffle that provides variable sound patterns is described. The baffle may support non-low frequency sound sources and a waveguide to provide varying sound beam patterns. The baffle may include a center mount adapted to receive a plurality of audio outputs and a plurality of low frequency apertures to receive a plurality low frequency output. The waveguide may be formed from a front face of the baffle. The front face may be intermediate the center mount and the low frequency apertures. The front face may include a continuously varying waveguide surface with a first waveguide portion adjacent a first audio output of the plurality of audio outputs providing a first sound pattern and a second waveguide portion adjacent a second audio output of the plurality of audio outputs providing a second sound pattern that is different than the first sound pattern.

A loudspeaker configured to provide asymmetrical beam coverage. A first group of drivers to outputs a first beam pattern. A second group of drivers, which is different from the first group of drivers, is configured to output a second beam pattern. A transmission line is adapted to output signals to the first driver group and the second driver group to provide an asymmetrical beam pattern. The first driver group outputs a beam pattern different than the second driver group. This can improve acoustic coverage, e.g., sound pressure levels, in the acoustic environment. In an example, the transmission line is separated into two distinct parts that feeds the first driver group and the second driver group respectively.

An acoustic focusing apparatus helps focus sound waves to target a predictable region. The predictable region may include the ears of a user. The acoustic focusing apparatus provides a plurality of transducers arranged in a planar array; whereas the transducers are on the same plane and mounted along parallel rows. The apparatus further provides a plurality of wave guides extending from a wave output surface on the transducers to focus the sound waves towards the predictable region. The apparatus utilizes at least one reflective portion that reflects the sound waves emitting from the wave guides towards the predictable region, and also helps diffuse and mask the source of the sound waves. In this manner, the apparatus focuses an audio signal directly at a person's ears so as to produce private, high fidelity stereo sound without use of headphones, while simultaneously not disturbing others within the same environment.

An embodiment of the invention provides a wireless in-ear utility device that rests in the user's ear canal near the user's eardrum. The in-ear utility device may be configured in a variety of ways, including, but in no way limited to a smart in-ear utility device, a flexible personal sound amplification product, a personal music player, a “walkie-talkie” and the like.