Included are a first obtainer which obtains a first signal output from a first microphone, a second obtainer which obtains a second signal output from a second microphone installed in a position different from a position where first microphone is installed, a delayer which delays the second signal, a mixed sounds estimator which estimates noises mixed in the first signal on the basis of the second signal delayed by the delayer, and an eraser which erases the noises from the first signal, the noises being estimated by the mixed sounds estimator.

A method and apparatus are provided for generating a directional output signal from sound received by at least two microphones arranged as microphone array. The method includes transforming the sound received by each of said microphones and represented by analog-to-digital converted time-domain signals provided by each of said microphones into corresponding complex-valued frequency-domain microphone signals each having a frequency component value for each of a plurality of frequency components, calculating, for each of the plurality of frequency components, real-valued Wind Reduction Factors as minima of the reciprocal and non-reciprocal frequency components of a plurality of real-valued Deviation Spectra if said minimum is below a preselected deviation threshold and set to one if said minimum is above or equal to said deviation threshold, and for each of the plurality of frequency components, forming a frequency-domain wind-reduced output signal.

A video system and method are presented that uses an output-receiving microphone mounted on the housing of the video system to receive a signal representative of the output of a speaker in a use-environment. This signal is compared with a second signal received from a spoken-word microphone that is mounted more remotely from the speaker. In some embodiments, the spoken-word microphone is positioned in a low-pass filter tune pipe and is combined with a separate spoken-word microphone in a tuned microphone array so as to filter out frequencies not associated with the human voice. The two signals are magnitude matched, and the first signal is subtracted from the second to generate an improved voice signal for a voice recognition system.

A system performs pole-zero or IIR modeling and estimation of an inter-microphone transfer function between first and second microphones that output respective first and second microphone signals. The system includes a first adaptive FIR filter to which the first microphone signal is provided, a delay element that delays the second microphone signal by a predetermined delay amount, and a second adaptive FIR filter to which the delayed second microphone signal is provided. A first coefficient of the second adaptive FIR filter is constrained to a fixed non-zero value. The filters are jointly adapted to minimize an error signal that is a difference of the two filters outputs. The delay is small: approximately the acoustic propagation delay between the two microphones and is not determined by the environmental reverberation characteristics. The error signal may serve as a noise reference in a noise canceller, for implementing far-field beamforming with low delay.

Translation device includes first microphone, first voice recognition circuit, first translation circuit, first voice synthesis circuit, first loudspeaker, second microphone, second voice recognition circuit, second translation circuit, second voice synthesis circuit, second loudspeaker, first echo canceller, second echo canceller, and control circuit. Control circuit causes first echo canceller to update a first transfer function used to estimate a first echo signal during a period in which a first translated voice is being output, and causes second echo canceller to update a second transfer function used to estimate a second echo signal during a period in which a second translated voice is being output.

An electronic device according to an embodiment may include: a first sound input device configured to obtain external sound and produce a first signal and a processor operatively connected to the first sound input device. The processor may be configured to: receive the first signal from the first sound input device; produce a first high-frequency signal by passing the first signal through a high-pass filter to; determine a first energy value of the first high-frequency signal; determine a second energy value of the first signal; compare a product of the second energy value of the first signal and the first energy value of the first high-frequency signal with a first threshold value to produce a first result; and determine whether the first sound input device is blocked based on the first result. In addition, various other embodiments may be provided.

A baby monitor system with white noise filtering comprises a camera unit and a monitor unit, wherein the camera unit is predefined soothing sounds and play at least one of the predefined soothing sounds for baby; the camera unit records the mixture sound of baby, ambient noises and white noises and transforms the mixture sound to sound features, wherein the white noises at least include the soothing sounds and stationary noise; the recorded sound features are compared to local audio features of the predefined soothing sounds; if there are matching features between the recorded sound features and the local audio features, removing the matching features from the recorded sound features; the stationary noise features are extracted and removed from the recorded sound features; the camera unit outputs the recorded mixture sound without the white noise to the monitor unit.

The amount of far-field noise transmitted by a primary communication device in an open-plan office environment is reduced by defining an acoustic perimeter of reference microphones around the primary device. Reference microphones generate a reference audio input including far-field noise in the proximity of the primary device. The primary device generates a main audio input including the voice of the primary speaker as well as background noise. Reference audio input is compared to main audio input to identify the background noise portion of the main audio signal. A noise reduction algorithm suppresses the identified background noise in the main audio signal. The one or more reference microphones defining the acoustic perimeter may be included in separate microphone devices placed in proximity to the main desktop phone, microphones within other nearby desktop telephone devices, or a combination of both types of devices.

Various embodiments of the present invention relate to a microphone, an electronic apparatus including the microphone and a method for controlling the microphone, the electronic apparatus comprising: a substrate comprising a first hole and a second hole into which an audio signal is input; a case that has a resonance space formed thereinside as a first side thereof is opened, a second side thereof is closed, and the first side is coupled with the substrate; a first audio generation unit that converts an audio signal input through a first hole of the substrate into an electrical signal, and comprises a first plate and a first membrane spaced apart from each other; a second audio generation unit that converts an audio signal input through a second hole of the substrate into an electrical signal, and comprises a second plate and a second membrane spaced apart from each other; a sound insulation wall that is disposed between the first audio generation unit and the second audio generation unit, and separates spaces of the first audio generation unit and the second audio generation unit as a first side thereof is coupled with the case and the second side thereof is coupled with the substrate; a microphone that is electrically connected to the first audio generation unit and the second audio generation unit, and comprises a signal processing unit for removing a noise signal exceeding a threshold value by analyzing the audio signals transmitted through the first audio generation unit and the second audio generation unit; and a processor that is electrically coupled with the microphone, wherein the sensitivity of the first audio generation unit is configured to be lower than the sensitivity of the second audio generation unit, so that the microphone can correctly receive the user's audio command by removing noise greater than or equal to a predetermined level. Various embodiments other than the various embodiments disclosed in the present invention are possible.

A device implementing an automatic speech recognition triggering system includes at least one processor configured to receive first and second audio signals respectively corresponding to first and second microphones of a device. The at least one processor is further configured to generate, based on at least one of the first or second audio signals, a third audio signal corresponding to a voice beam directed to an expected position of a mouth of a user. The at least one processor is further configured to determine whether wind noise is present in at least one of the first, second, or third audio signals. The at least one processor is further configured to, based on determining whether wind noise is present, an audio signal from among the second or third audio signals, for a determination of whether at least one of the first or second audio signals corresponds to the user.