Abstract: A personalized voice conversion system includes a cloud server and an intelligent device that communicates with the cloud server. The intelligent device upstreams an original voice signal to the cloud server. The cloud server converts the original voice signal into an intelligible voice signal based on an intelligible voice conversion model. The intelligent device downloads and plays the intelligible voice signal. Based on the original voice signal and the corresponding intelligible voice signal, the cloud server and the intelligent device train an off-line voice conversion model provided to the intelligent device. When the intelligent device stops communicating with the cloud server, the intelligent device converts a new original voice signal into a new intelligible voice signal based on the off-line voice conversion model and plays the new intelligible voice signal.

Abstract: A personalized voice conversion system includes a cloud server and an intelligent device that communicates with the cloud server. The intelligent device upstreams an original voice signal to the cloud server. The cloud server converts the original voice signal into an intelligible voice signal based on an intelligible voice conversion model. The intelligent device downloads and plays the intelligible voice signal. Based on the original voice signal and the corresponding intelligible voice signal, the cloud server and the intelligent device train an off-line voice conversion model provided to the intelligent device. When the intelligent device stops communicating with the cloud server, the intelligent device converts a new original voice signal into a new intelligible voice signal based on the off-line voice conversion model and plays the new intelligible voice signal.

Abstract: A device and a method for clarifying dysarthria voices is disclosed. Firstly, a dysarthria voice signal is received and framed to generate dysarthria frames. Then, the dysarthria frames are received to retrieve dysarthria features. Finally, the dysarthria features are received. Without receiving phases corresponding to the dysarthria features, the dysarthria features are converted into an intelligent voice signal based on an intelligent voice conversion model. The intelligent voice conversion model is not trained by the dynamic time warping (DTW). The present invention avoids the phase distortion of the voice signal and provides more natural and clarified voices with low noise.

Abstract: A system for improving dysarthria speech intelligibility and method thereof, are provided. In the system, user only needs to provides a set of paired corpus including a reference corpus and a patient corpus, and a speech disordering module can automatically generate a new corpus completely synchronous with the reference corpus, and the new corpus can be used as a training corpus for training a dysarthria voice conversion model. The present invention does not need to use a conventional corpus alignment technology or a manual manner to perform pre-processing on the training corpus, so that manpower cost and time cost can be reduced, and synchronization of the training corpus can be ensured, thereby improving both training and conversion qualities of the voice conversion model.

Abstract: A device and a method for clarifying dysarthria voices is disclosed. Firstly, a dysarthria voice signal is received and framed to generate dysarthria frames. Then, the dysarthria frames are received to retrieve dysarthria features. Finally, the dysarthria features are received. Without receiving phases corresponding to the dysarthria features, the dysarthria features are converted into an intelligent voice signal based on an intelligent voice conversion model. The intelligent voice conversion model is not trained by the dynamic time warping (DTW). The present invention avoids the phase distortion of the voice signal and provides more natural and clarified voices with low noise.

Abstract: A device and a method for generating synchronous corpus is disclosed. Firstly, script data and a dysarthria voice signal having a dysarthria consonant signal are received and the position of the dysarthria consonant signal is detected, wherein the script data have text corresponding to the dysarthria voice signal. Then, normal phoneme data corresponding to the text are searched and the text is converted into a normal voice signal based on the normal phoneme data corresponding to the text. The dysarthria consonant signal is replaced with the normal consonant signal based on the positions of the normal consonant signal and the dysarthria consonant signal, thereby synchronously converting the dysarthria voice signal into a synthesized voice signal. The synthesized voice signal and the dysarthria voice signal are provided to train a voice conversion model, retain the timbre of the dysarthria voices and improve the communication situations.

Abstract: A device and a method for generating synchronous corpus is disclosed. Firstly, script data and a dysarthria voice signal having a dysarthria consonant signal are received and the position of the dysarthria consonant signal is detected, wherein the script data have text corresponding to the dysarthria voice signal. Then, normal phoneme data corresponding to the text are searched and the text is converted into a normal voice signal based on the normal phoneme data corresponding to the text. The dysarthria consonant signal is replaced with the normal consonant signal based on the positions of the normal consonant signal and the dysarthria consonant signal, thereby synchronously converting the dysarthria voice signal into a synthesized voice signal. The synthesized voice signal and the dysarthria voice signal are provided to train a voice conversion model, retain the timbre of the dysarthria voices and improve the communication situations.

Abstract: A system for improving dysarthria speech intelligibility and method thereof, are provided. In the system, user only needs to provides a set of paired corpus including a reference corpus and a patient corpus, and a speech disordering module can automatically generate a new corpus completely synchronous with the reference corpus, and the new corpus can be used as a training corpus for training a dysarthria voice conversion model. The present invention does not need to use a conventional corpus alignment technology or a manual manner to perform pre-processing on the training corpus, so that manpower cost and time cost can be reduced, and synchronization of the training corpus can be ensured, thereby improving both training and conversion qualities of the voice conversion model.

Abstract: A method and a device for retrieving a breathing signal is disclosed. Firstly, a triaxial acceleration signal is retrieved for a fixed period. Then, multivariate empirical mode decomposition (MEMD) is performed on the triaxial acceleration signal, so as to sequentially obtain a plurality of intrinsic mode functions (IMFs). Finally, an average inclination angle of the triaxial acceleration signal corresponding to each intrinsic mode function is sequentially calculated, and the intrinsic mode function corresponding to the average inclination angle within a predetermined angle range is added to a set. All the intrinsic mode functions are added up to obtain and output a breathing signal when an amount of the intrinsic mode functions in the set equals to a predetermined value being a natural number.

Abstract: A video device for realtime pedaling frequency estimation is mounted on a bike and comprises an image capture unit capturing continuous dynamic images of an upper body of a biker; an image recognition unit recognizing images of symmetric regions of the biker and images of swings of the symmetric regions from the continuous dynamic images; a microprocessor calculating a frequency of periodical swings of the biker from the images of the symmetric regions and the images of the swings of the symmetric regions, and then obtaining a pedaling frequency; and a display device presenting the pedaling frequency, wherein a widely-used intelligent handheld device replaces the sensors, display device, and complicated circuits of the conventional cyclometer, and wherein a novel image recognition technology is used to measure the pedaling frequency with a considerable accuracy in a lower cost and a convenient way.

Abstract: A video device for realtime pedaling frequency estimation is mounted on a bike and comprises an image capture unit capturing continuous dynamic images of an upper body of a biker; an image recognition unit recognizing images of symmetric regions of the biker and images of swings of the symmetric regions from the continuous dynamic images; a microprocessor calculating a frequency of periodical swings of the biker from the images of the symmetric regions and the images of the swings of the symmetric regions, and then obtaining a pedaling frequency; and a display device presenting the pedaling frequency, wherein a widely-used intelligent handheld device replaces the sensors, display device, and complicated circuits of the conventional cyclometer, and wherein a novel image recognition technology is used to measure the pedaling frequency with a considerable accuracy in a lower cost and a convenient way.

Abstract: A tone mapping (TM) method of high dynamic range (HDR) image/video includes the steps of A) acquiring an HDR image/video; B) processing the HDR image/video via fast global TM where each of processed pixel outputs is denoted by PixelFG and then computing the HDR image/video via block-based GC algorithm where each of processed pixel outputs is denoted by PixelBGC; and C) computing the pixel outputs PixelFG and the pixel outputs PixelBGC that each pixel corresponds to respectively as presented by ?×PixelFG+?×PixelBGC where the numeral values of ? and ? are between 0 and 1 each and ?+?=1. After the computation, the result is the final output result.

Abstract: A data processing method for a context formation module and an arithmetic encoder in an embedded block coding with optimized truncation (EBCOT) module includes inputting column-based data into the context formation module, controlling the context formation module with a finite state so that the context formation module has a constant valid output in each clock cycle, separating the calculation and the normalization operation of registers into different pipeline stages of the arithmetic encoder, and interleaving inputs so that two different data are inputted into the arithmetic encoder in one clock cycle difference.

Abstract: An apparatus for processing an image with a discrete wavelet transform is provided. For one-dimensional circuit, the method changes conventional image data processing flow and uses common product of sequential calculations with respect to the time axis. The calculations for input data are not repeated so that components of the hardware architecture are minimized. For two-dimensional circuit, the method uses an external data scanning method to eliminate an external memory, transposing buffer, from a transforming circuit.

Abstract: A dynamic NP-swappable body bias circuit includes a core circuit, a power switch and a body bias controller. The core circuit includes a body bias terminal. The power switch includes a body bias terminal, and connects the core circuit to an external voltage supply. The body bias controller is connected to the body bias terminals of the core circuit and the power switch so that the power switch and the core circuit are under the control of the body bias controller.

Abstract: A decoding apparatus for Booth multiplication includes a NAND gate, a first and a second OR gate coupled to the NAND gate, a first and a second exclusive NOR gate coupled respectively to the OR gates, a clean-to-zero device coupled to the first and the second OR gates, and a send-one device coupled to the NAND gate. The clean-to-zero device permits the decoding apparatus to deliver a zero. The send-one device permits the decoding apparatus to deliver a one. The decoding apparatus supports both signed and unsigned Booth multiplications.

Abstract: An apparatus for processing an image with a discrete wavelet transform is provided. For one-dimensional circuit, the method changes conventional image data processing flow and uses common product of sequential calculations with respect to the time axis. The calculations for input data are not repeated so that components of the hardware architecture are minimized. For two-dimensional circuit, the method uses an external data scanning method to eliminate an external memory, transposing buffer, from a transforming circuit.

Abstract: A data processing method for a context formation module and an arithmetic encoder in an embedded block coding with optimized truncation (EBCOT) module includes inputting column-based data into the context formation module, controlling the context formation module with a finite state so that the context formation module has a constant valid output in each clock cycle, separating the calculation and the normalization operation of registers into different pipeline stages of the arithmetic encoder, and interleaving inputs so that two different data are inputted into the arithmetic encoder in one clock cycle difference.

Abstract: A low power dynamic logic circuit. By shifting a discharge NMOS transistor of a conventional dynamic logic circuit between an output terminal and a logic block, plus an additional charge and discharge control, the operation speed and power consumption of a dynamic circuit can be effectively improved. Using the charge redistribution to speed up the circuit operation and to reduce the body effect that affects the operation speed, the speed of the novel dynamic logic circuit is enhanced. By transferring the lump capacitor of the charge/discharge, the dynamic power can be effectively reduced. The lower power dynamic logic circuit can be used independently or combined with a conventionally dynamic logic circuit.

Abstract: A low power dynamic logic circuit. By shifting a discharge NMOS transistor of a conventional dynamic logic circuit between an output terminal and a logic block, plus an additional charge and discharge control, the operation speed and power consumption of a dynamic circuit can be effectively improved. Using the charge redistribution to speed up the circuit operation and to reduce the body effect that affects the operation speed, the speed of the novel dynamic logic circuit is enhanced. By transferring the lump capacitor of the charge/discharge, the dynamic power can be effectively reduced. The lower power dynamic logic circuit can be used independently or combined with a conventionally dynamic logic circuit.