Abstract: A noise-suppression device includes an input buffer, a spatial filter, a delay buffer, and a controller. The input buffer stores sound data. The spatial filter generates processed data by using an internal adaptive control according to a control signal. The delay buffer stores the processed data. The controller operates in either one of a training stage, a flushing stage, or a normal stage and generates the control signal. When the controller operates in the training stage, the spatial filter receives the sound data from the input buffer to generate the processed data which is continuously processed by the spatial filter and then stored in the delay buffer over and over again until the internal adaptive control is converged.

Abstract: A method of speech enhancement for target speakers is presented. A blind source separation (BSS) module is used to separate a plurality of microphone recorded audio mixtures into statistically independent audio components. At least one of a plurality of speaker profiles are used to score and weight each audio components, and a speech mixer is used to first mix the weighted audio components, then align the mixed signals, and finally add the aligned signals to generate an extracted speech signal. Similarly, a noise mixer is used to first weight the audio components, then mix the weighted signals, and finally add the mixed signals to generate an extracted noise signal. Post processing is used to further enhance the extracted speech signal with a Wiener filtering or spectral subtraction procedure by subtracting the shaped power spectrum of extracted noise signal from that of the extracted speech signal.

Abstract: A noise-suppression device includes an input buffer, a spatial filter, a delay buffer, and a controller. The input buffer stores sound data. The spatial filter generates processed data by using an internal adaptive control according to a control signal. The delay buffer stores the processed data. The controller operates in either one of a training stage, a flushing stage, or a normal stage and generates the control signal. When the controller operates in the training stage, the spatial filter receives the sound data from the input buffer to generate the processed data which is continuously processed by the spatial filter and then stored in the delay buffer over and over again until the internal adaptive control is converged.

Abstract: A microphone array disposed on a two-piece computer is provided. The two-piece computer has a first piece with a keyboard disposed thereon and a second piece with a display screen disposed thereon. The microphone array has two microphones, which are both disposed on the first piece, wherein a connecting line of the two microphones is not vertical to a normal line of the display screen of the second piece.

Abstract: A sound source monitoring system includes a sound receiving module, a sound detection module, a sound source localization module, and a camera module. The sound receiving module is configured to receive a plurality of sound signals. The sound detection module is for dividing an integrated signal formed by adding the sound signals received by the sound receiving module and normalizing the sum of the sound signals or dividing each of the sound signals into a plurality of sub-bands, calculating a signal-to-noise ratio (SNR) of each sub-band and a background noise, and accordingly determining whether to output the sound signals received by the sound receiving module to the sound source localization module. The sound source localization module is for outputting a sound source location by using the sound signals received by the sound receiving module. The camera module is for shooting an image corresponding to the sound source location.

Abstract: A microphone array disposed on a two-piece computer is provided. The two-piece computer has a first piece with a keyboard disposed thereon and a second piece with a display screen disposed thereon. The microphone array has two microphones, which are both disposed on the first piece, wherein a connecting line of the two microphones is not vertical to a normal line of the display screen of the second piece.

Abstract: A particle filter is suitable for performing particle filtering on a frame to track a particular object in the frame. The particle filter includes a frame cache, an observation model generator, and a particle filter controller. The frame cache is connected to a system memory through a system bus, in which the system memory stores all image blocks of the frame; and the frame cache obtains the at least one image block of the frame from the system memory and stores the obtained image block. The observation model generator reads at least one pixel from the frame cache, and generates an observation model corresponding to the object and the read image block according to the read pixel. The particle filter controller obtains the observation model from the observation model generator, and determines and outputs an object tracking result of the object according to the observation model.

Abstract: A sound source monitoring system includes a sound receiving module, a sound detection module, a sound source localization module, and a camera module. The sound receiving module is configured to receive a plurality of sound signals. The sound detection module is for dividing an integrated signal formed by adding the sound signals received by the sound receiving module and normalizing the sum of the sound signals or dividing each of the sound signals into a plurality of sub-bands, calculating a signal-to-noise ratio (SNR) of each sub-band and a background noise, and accordingly determining whether to output the sound signals received by the sound receiving module to the sound source localization module. The sound source localization module is for outputting a sound source location by using the sound signals received by the sound receiving module. The camera module is for shooting an image corresponding to the sound source location.

Abstract: A method and an electronic device for reducing digital image noises are described. The method includes the steps of sequentially selecting a pixel from a digital image, and setting the pixel as a target pixel; defining a first area, and setting at least two of the rest pixels surrounding the target pixel in the first area as adjacent pixels; setting a first weighted area; setting a second weighted area corresponding to the first weighted area; computing a weight of the adjacent pixel located at a center position of the second weighted area by using a piecewise linear curve according to a similarity value of the first weighted area and the second weighted area; computing a weighted average of all the adjacent pixels and the target pixel, to determine a new value of the target pixel; and performing the above steps repeatedly, till all the pixels are processed.

Abstract: A moving object detection method using image contrast enhancement includes receiving a source image, in which each pixel has a pixel illumination value; processing the source image using an image contrast enhancement procedure; executing a change detection procedure to compare a background model and the source image being processed using the image contrast enhancement procedure, and outputting a detection result accordingly; and executing a background and foreground separation procedure to output a moving object according to the detection result.

Abstract: A method and an electronic device for reducing digital image noises are described. The method includes the steps of sequentially selecting a pixel from a digital image, and setting the pixel as a target pixel; defining a first area, and setting at least two of the rest pixels surrounding the target pixel in the first area as adjacent pixels; setting a first weighted area; setting a second weighted area corresponding to the first weighted area; computing a weight of the adjacent pixel located at a center position of the second weighted area by using a piecewise linear curve according to a similarity value of the first weighted area and the second weighted area; computing a weighted average of all the adjacent pixels and the target pixel, to determine a new value of the target pixel; and performing the above steps repeatedly, till all the pixels are processed.

Abstract: A method for analyzing energy consistency to process data, for use with an electronic apparatus, includes the steps of analyzing energy consistency to process data, performing a data-buffering process for outputting a data frame, performing a data-processing process for outputting a shaping residual after inputting the data frame, performing an energy-framing process for dividing the shaping residual into N sub-blocks after inputting the shaping residual to calculate energy of N sub-blocks to get a plurality of energy coefficients, performing a consistency-checking process for inputting the energy coefficients to check whether the energy coefficients can fulfill a threshold screening for consistency, enerating the decision about the data frame which should be processed by the long-type window coding if the spectral characteristics are consistent wherein the energy coefficients conform to the consistent energy relationship, and generating the decision about the data frame should be processed by the short-type

Abstract: A method for analyzing energy consistency to process data, for use with an electronic apparatus, includes the steps of analyzing energy consistency to process data, performing a data-buffering process for outputting a data frame, performing a data-processing process for outputting a shaping residual after inputting the data frame, performing an energy-framing process for dividing the shaping residual into N sub-blocks after inputting the shaping residual to calculate energy of N sub-blocks to get a plurality of energy coefficients, performing a consistency-checking process for inputting the energy coefficients to check whether the energy coefficients can fulfill a threshold screening for consistency, enerating the decision about the data frame which should be processed by the long-type window coding if the spectral characteristics are consistent wherein the energy coefficients conform to the consistent energy relationship, and generating the decision about the data frame should be processed by the short-type