105 results about "Sound separation" patented technology

A system and method for noise cancellation is disclosed herein generally having at least one microphone, a processor, and a speaker array. The processor may contain an adaptive filtering feature, to separate desirable sound from undesirable sound. The undesirable sound may be suppressed by the processor by creating a canceling waveform and transmitting the canceling waveform to the user's head via a speaker array. The desirable sound may be enhanced by increasing the amplitude of the waveform and transmitting the amplified waveform to the user's head via a speaker array. The sound transmitted to the user's head by the system may be localized using an image tracking subsystem and speaker array. The image tracking system may track the actual visible image or alternatively a heat (e.g. infrared) image of the user's head.

A loudspeaker configuration capable of generating stereophonic sound separation from relatively loudspeaker drivers that are not necessarily widely separated. For example, such a loudspeaker configuration can be used to generate relatively good sound separation from a single chassis, such as a single speaker box, a boom box, a clock radio or the like. This can advantageously save space in many environments. One embodiment uses four mid-tweeter speaker drivers and a bass driver. The four mid-tweeter speaker drivers are arranged facing outward approximately 90 degrees apart from each other. A speaker driver facing the listener reproduces a mid channel signal, for example, L+R. A speaker driver facing away from the listener reproduces the same mid channel signal or a delayed version of the mid channel signal. A left facing speaker reproduces a side channel, for example, L−R. A right facing speaker reproduces a side channel, for example, R−L. The acoustic combination of the sound produced by the four speaker drivers creates a virtual left and right loudspeaker as experienced by the listener.

The present invention is directed to providing a sound field reproduction system that can enhance the sound separation between the front and rear seats or left and right seats of a vehicle. The sound field reproduction system includes a control unit for creating a first sound signal and a second sound signal from one or a plurality of sources, a narrow-directional speaker mounted on the front seat side of the vehicle, a speaker mounted on the rear seat side of the vehicle, and a signal processing unit for driving the narrow-directional speaker based on the first sound signal that has been processed according to frequency range, and for driving the speaker based on the second sound signal.

There is provided a sound processing apparatus including a sound separation unit that separates an input sound into a plurality of sounds caused by a plurality of sound sources, a sound type estimation unit that estimates sound types of the plurality of sounds separated by the sound separation unit, a mixing ratio calculation unit that calculates a mixing ratio of each sound in accordance with the sound type estimated by the sound type estimation unit, and a sound mixing unit that mixes the plurality of sounds separated by the sound separation unit in the mixing ratio calculated by the mixing ratio calculation unit.

The invention provides a method for sound field separation by double plane vibration speed measurement and two dimensional space Fourier transform, which is characterized in that a measurement plane S1 and an auxiliary measurement plane S2 parallel therewith and Delta h away therefrom are disposed in the measurement sound field; normal direction particle vibration speed is measured on two planes; wave number domain transfer relationship between normal direction particle vibration speed on two measurement planes is established by the two dimensional space Fourier transform; sound pressure, normal direction particle vibration speed radiated by sound sources on both sides of the two measurement planes is separated according to the transferring relation. The method adopts two dimensional space Fourier transform as the sound field separation algorithm, making computation speed fast, and implementation simple; normal direction particle vibration speed on two measurement plane is used as the input for separation, so that the separated normal direction particle vibration speed has higher accuracy comparing with using sound pressure on two measurement planes as the input. The method can be widely applied for near-field acoustic holographic measurement under internal sound field or noise environment, material reflection coefficient measurement, scattering sound field separation.

The invention discloses a method for separating a speed changer knocking structure noise and an air noise based on a transmission path. The method comprises the following steps: knocking noise acquisition under an acceleration condition, a finished automobile sound transmission function test and knocking air radiation sound and structure transmission sound separation. By using the method, sizes of the structure noise and the air noise in the speed changer knocking noise transmitted to the automobile can be objectively and accurately separated.

The invention discloses a sound separation method, which comprises the following steps of: dividing an original audio and video sample into a plurality of audio and video segments, and extracting a video stream and an audio stream of each audio and video segment; determining face features in the video stream of each audio and video segment; obtaining audio features in the audio stream of each audio/video segment by using an audio conversion compression method; combining the face features and the audio features of each audio and video segment to generate audio-visual features of each audio and video segment; taking the audio-visual characteristics of each audio-video segment as the input of a sound separation model, and training the sound separation model to obtain a trained sound separation model; and taking the target audio and video data as input of the trained sound separation model, and outputting audio data of a person in the target audio and video data. The invention further provides a sound separation device and a computer readable storage medium. According to the invention, the accurate mapping of the sound and the speaker can be realized, and the voice separation quality is obviously improved.

The invention designs a device for realizing acoustic agglomeration emission reduction of fine particles in high-flow flue gas of a burning energy system. The device comprises a high-pressure gas flow source, a high-pressure gas mixing chamber, gas flow sound sources, a horn, a coupling cabin, an agglomeration cabin, an extended cabin, a movable end surface, a conventional dust remover, a data sensing control part, a central measurement and control computer, a sound elimination part and a sound insulation part. According to the device, the three high-power gas flow sound sources are matched with a variable-section pipeline by fully utilizing the principle that the acoustic agglomeration efficiency is sharply improved along with the increment of the sound pressure level; a barrier structure and a gas-sound separation part are introduced, so that the fine particles are quickly agglomerated in the large-size agglomeration cabin under the action of a high-strength and low-harmonic-component planar standing wave sound field; running parameters are adjusted and optimized in a unified manner by virtue of the measurement and control computer; the best transmission efficiency of strong sound waves from generating to acting is realized and the characteristic change of the fine particles is adapted; the whole realization scheme has the advantages of emission reduction efficiency, economical efficiency, applicability, no pollution, extendability and the like.

In a source sound separator, first and second target sound predominant spectra are generated respectively by first and second processing operations for linear combination for emphasizing the target sound, using received sound signals of two microphones arrayed at a distance from each other. A target sound suppressed spectrum is generated by processing for linear combination for suppression of the target sound, using the two received sound signals. Further, a phase signal containing a larger amount of signal components of the target sound and exhibiting directivity in the direction of the target sound is generated by processing of linear combination, using the two received sound signals. The target sound and the interfering sound are separated from each other using the first and second target sound predominant spectra, the target sound suppressed spectrum, and the phase signal.

A sound processing apparatus includes a sound determination portion operable to determine whether an input sound includes a first sound emitted from a particular source based on location information of the source, a sound separation portion operable to separate the input sound into the first sound and a second sound emitted from a source different from the particular source if the sound determination portion determines that the input sound includes the first sound, and a sound mixing portion operable to mix the first sound and the second sound separated by the sound separation portion at a prescribed volume ratio.

The invention relates to an ultrasonic Doppler poly-phase flow velocity distribution detecting device, which is used to measure the flow velocity distribution of the cross section of the fluid inside a to-be-detected pipeline. The device comprises an ultrasonic sensor array and an ultrasonic signal generating and detecting unit. The ultrasonic sensor array consists of a plurality of ultrasonic probes distributed uniformly on the positions of the same cross section of the to-be-detected pipeline and each ultrasonic probe is structured by two ultrasonic transducers with sound wedge. Between the two ultrasonic transducers, a sound separation layer is placed to isolate sounds. One of the ultrasonic transducers serves as an ultrasonic emission transducer and is fixedly arranged on the surface of the transparent wedge in parallel to the axial direction of the pipeline while the other serves as an ultrasonic reception transducer and is fixedly inclined on the surface of the transparent wedge of the axial direction of the pipeline. When the device measures, in a certain order, the emission transducers in the ultrasonic probes are excited in succession, and under each excitation, all the reception transducers receive the ultrasonic echo signals at the same time, and under the same cross section and through multi-direction excitation, the multi-direction synthesized ultrasonic Doppler frequency shift projection information about the flow velocity of the fluid inside the testing pipeline can be obtained.

The invention discloses granite waste stone dust foam ceramics comprising the following components by the weight percentage: 70.0-85.0% of granite waste, 2.0-8.0% of china clay tailings, 4.0-14.5% ofwaste ceramic powder, 3.0-10.0% of clay, and 0.5-3.0% of a high-temperature foaming agent; the invention also discloses a preparation method of the granite waste stone dust foam ceramics. The preparation method has the advantages of simple process and low production cost; the prepared foam ceramics have the advantages of small density, low heat conductivity coefficient and high strength, and alsohave remarkable and excellent performance of aging resistance, corrosion resistance, heat insulation and heat preservation, sound separation and absorption, water resistance and fire prevention, and green and environmental protection, and are suitable for the field of building heat preservation; the mixture can be directly put in a refractory material mould and then is sent into a high temperaturefurnace and calcined, and the granite waste stone dust foam ceramics are prepared; the forming process is simplified, the work efficiency is improved, and the granite waste stone dust foam ceramics are suitable for mass production.

The embodiment of the invention discloses a method and device of processing face images, comprising: converting a pending image into an HSV color space from an RGB color space; obtaining the skin color area of the pending image according to the H component threshold in the HSV color space; converting the HSV color space into a skin color likelihood image, and performing binary segmentation on the skin color likelihood image; obtaining a face candidate image having a skin color area and a non skin color area separated according to the skin color likelihood image after binary segmentation and the skin color area of the pending image; and marking the skin color area in the face candidate image. The method and device utilize the chroma, brightness and saturation in the HSV color space to perform sound separation, realize less overlapping between skin color points and non skin color points, and improve detection precision; in addition, the method and device utilize an H-SGM skin color model to eliminate the interference of the non skin color area and most background area, and divide a candidate face area so as to realize high face detection precision and less misdetection.