Abstract: Provided are a multi-stage speech recognition apparatus and method. The multi-stage speech recognition apparatus includes a first speech recognition unit performing initial speech recognition on a feature vector, which is extracted from an input speech signal, and generating a plurality of candidate words; and a second speech recognition unit rescoring the candidate words, which are provided by the first speech recognition unit, using a temporal posterior feature vector extracted from the speech signal.

Abstract: One aspect of the invention relates to a methacrylate resin prepared by suspension polymerization using a polyalkylacrylate-acrylic acid as a suspension stabilizer. The suspension stabilizer is used in an amount of about 0.05 to about 0.25 parts by weight per 100 parts by weight of a monomer mixture. Another aspect of the invention relates to a method for preparing a methacrylate resin, which comprises: preparing a mixture by mixing an initiator and a chain-transfer agent with a monomer mixture comprising at least about 50% by weight of alkyl methacrylate; and adding the mixture to an aqueous solution of polyalkylacrylate-acrylic acid to conduct suspension polymerization.

Abstract: Provided is a method and apparatus for transforming a speech feature vector. The method includes extracting a feature vector required for speech recognition from a speech signal and transforming the extracted feature vector using an auto-associative neural network (AANN).

Abstract: A formant frequency estimation method which is important information in speech recognition by accelerating a spectrum using a pitch frequency, and an apparatus using the method is provided. That is, the formant frequency estimation method includes preprocessing an input speech signal and generating a spectrum by a fast Fourier transforming the preprocessed input speech signal; smoothing the generated spectrum; accelerating the smoothed spectrum; and determining a formant frequency on the basis of the accelerated spectrum.

Abstract: A recognition confidence measurement method, medium and system which can more accurately determine whether an input speech signal is an in-vocabulary, by extracting an optimum number of candidates that match a phone string extracted from the input speech signal and estimating a lexical distance between the extracted candidates is provided. A recognition confidence measurement method includes: extracting a phoneme string from a feature vector of an input speech signal; extracting candidates by matching the extracted phoneme string and phoneme strings of vocabularies registered in a predetermined dictionary and; estimating a lexical distance between the extracted candidates; and determining whether the input speech signal is an in-vocabulary, based on the lexical distance.

Abstract: A method of measuring confidence of speech recognition in a speech recognizer compares a phase change point with a phoneme string change point and uses a difference between the phase change point and the phoneme string change point and a likelihood ratio, and an apparatus using the method is provided. That is, the method of the present invention includes detecting a phase change point of a speech signal; detecting a phoneme string change point according to a result of speech recognition; calculating confidence of the speech recognition by using a difference between the detected phase change point and phoneme string change point. According to the present invention, a performance of measuring confidence may become improved by simultaneously taking not only a likelihood ratio, but also taking a comparison result of a phase change point with a phoneme string change point into consideration.

Abstract: A method and apparatus of estimating a voicing for speech recognition by using local spectral information. The voicing estimation method for speech recognition includes performing a Fourier transform on input voice signals after performing pre-processing on the input voice signals. The method further includes detecting peaks in the input voice signals after smoothing the input voice signals. The method also includes computing every frequency bound associated with the detected peaks, and determining a class of a voicing according to each computed frequency bound.

Abstract: A method and an apparatus for detecting a pitch in input voice signals by using a spectral auto-correlation. The pitch detection method includes: performing a Fourier transform on the input voice signals after performing a pre-processing on the input voice signals, performing an interpolation on the transformed voice signals, calculating a spectral difference from a difference between spectrums of the interpolated voice signals, calculating a spectral auto-correlation by using the calculated spectral difference, determining a voicing region based on the calculated spectral auto-correlation, and extracting a pitch by using the spectral auto-correlation corresponding to the voicing region.

Abstract: An apparatus for speech recognition includes: a first confidence score calculator calculating a first confidence score using a ratio between a likelihood of a keyword model for feature vectors per frame of a speech signal and a likelihood of a Filler model for the feature vectors; a second confidence score calculator calculating a second confidence score by comparing a Gaussian distribution trace of the keyword model per frame of the speech signal with a Gaussian distribution trace sample of a stored corresponding keyword of the keyword model; and a determination module determining a confidence of a result using the keyword model in accordance with a position determined by the first and second confidence scores on a confidence coordinate system.

Abstract: A class-D power amplifier, which prevents excessive response phenomenon from occurring when returning to a steady state from an abnormal state and an amplification method of the class-D power amplifier are provided. The class-D power amplifier prevents an integral control circuit or a proportional integral control circuit from becoming saturated by using sub-negative feedback loop operations, without using a high-capacity output blocking switch in an initial state or an abnormal state. Thus, suppressing pop noise due to the excessive response phenomenon caused when the class-D power amplifier returns to the steady state from the initial state or the abnormal state and reducing power consumption.

Abstract: Disclosed herein is a method and apparatus to recognize speech by measuring the confidence levels of respective frames. The method includes the operations of obtaining frequency features of a received speech signal for the respective frames having a predetermined length, calculating a keyword model-based likelihood and a filler model-based likelihood for each of the frame, calculating a confidence score based on the two types of likelihoods, and deciding whether the received speech signal corresponds to a keyword or a non-keyword based on the confidence scores. Also, the method includes the operation of transforming the confidence scores by applying transform functions of clusters, which include the confidence scores or are close to the confidence scores, to the confidence scores.

Abstract: Disclosed is a digital PWM input D class amplifier by PWM negative feedback. The amplifier includes: digital modulation part for modulating PCM signal of input audio to PWM signal; pulse width generating and correcting part for comparing difference between the PWM signal and output signal negatively fed back, with PWM ramp signal to generate PWM switching signal; output part for generating an amplified output audio signal in response to the PWM switching signal of the pulse width generating and correcting part; and voltage negative feedback loop for negatively feeding back signal of the output part and decreasing a harmonic component to provide the signal to the pulse width generating and correcting part. Thus, the invention compares the negative feedback signal with positive/negative (+/?) saw tooth PWM ramp signal to control On/Off time period of switching transistor and the PWM pulse width and thereby enhance the linearity of the output PWM.

Abstract: Disclosed is a digital PWM input D class amplifier by PWM negative feedback. The amplifier includes: digital modulation part for modulating PCM signal of input audio to PWM signal; pulse width generating and correcting part for comparing difference between the PWM signal and output signal negatively fed back, with PWM ramp signal to generate PWM switching signal; output part for generating an amplified output audio signal in response to the PWM switching signal of the pulse width generating and correcting part; and voltage negative feedback loop for negatively feeding back signal of the output part and decreasing a harmonic component to provide the signal to the pulse width generating and correcting part. Thus, the invention compares the negative feedback signal with positive/negative (+/?) saw tooth PWM ramp signal to control On/Off time period of switching transistor and the PWM pulse width and thereby enhance the linearity of the output PWM.

Abstract: A class-D power amplifier, which prevents excessive response phenomenon from occurring when returning to a steady state from an abnormal state and an amplification method of the class-D power amplifier are provided. The class-D power amplifier prevents an integral control circuit or a proportional integral control circuit from becoming saturated by using sub-negative feedback loop operations, without using a high-capacity output blocking switch in an initial state or an abnormal state. Thus, suppressing pop noise due to the excessive response phenomenon caused when the class-D power amplifier returns to the steady state from the initial state or the abnormal state and reducing power consumption.

Abstract: A tomographic apparatus for obtaining a cross-sectional image by fixing an X-ray source, and synchronously rotating an object under examination and a detector. According to the apparatus, the slope angle of the X-ray source can be sufficiently enlarged by the adjustment of the X-ray tube, and thus the precision of the obtained cross-sectional image can be heightened. Also, a method of obtaining a cross-sectional image of a three-dimensional object from an arbitrary direction and height.

Abstract: A horizontal deflection amplifying apparatus for use in an automatic main power supply such as that for a cathode ray tube is provided. The apparatus uses a microprocessor for the connection of capacitors to a horizontal deflection coil (yoke coil) by controlling the switching operation of relay switches. To prevent the drive transistor of the deflection coil driver from being destroyed or the horizontal deflection coil from being damaged due to excess current, the capacitors are connected or disconnected while the power supply voltage is off (i.e., at a 0V state) and the supply voltage is then re-applied. Thus, the horizontal deflection amplifying apparatus can be safely driven.