Abstract: A method, medium, and apparatus for extracting a target sound from mixed sound. The method includes receiving a mixed signal through a microphone array, generating a first signal whose directivity is emphasized toward a target sound source and a second signal whose directivity toward the target sound source is suppressed based on the mixed signal, and extracting a target sound signal from the first signal by masking an interference sound signal, which is contained in the first signal, based on a ratio of the first signal to the second signal. Therefore, a target sound signal can be clearly separated from a mixed sound signal which contains a plurality of sound signals and is input to a microphone array.

Abstract: A method and apparatus for measuring a distance to a sound source. The method includes combining sound source signals input through at least two microphones and generating at least two microphone output signals, and performing an operation on the generated microphone output signals and calculating a distance to a sound source by using the relationship between a result of the operation and a frequency of the input sound source signals. Accordingly, regardless of the strength of a sound source, the distance to a sound source can be measured.

Abstract: A method and apparatus for discriminating sound sources from a mixed sound is provided. The method includes separating sound source signals from a mixed sound signal including a plurality of sound source signals that are input through a microphone array, estimating a transfer function of a mixing channel mixing the plurality of sound source signals from relationships between the mixed sound signal and the separated sound source signals, obtaining input signals of the microphone array by multiplying the estimated transfer function by the separated sound source signals, and calculating location information of each sound source using a predetermined sound source location estimation method based on the obtained input signals.

Abstract: A sound zoom method, medium, and apparatus generating a signal in which a target sound is removed from sound signals input to a microphone-array by adjusting a null width that restricts a directivity sensitivity of the microphone array, and extracting a signal corresponding to the target sound from the sound signals by using the generated signal. Thus, a sound located at a predetermined position away from the microphone array can be selectively obtained so that a target sound is efficiently obtained.

Abstract: A method for performing a one-to-many file transfer in a converged IP messaging system includes receiving a list of target receiving terminals from a transmitting terminal; verifying whether the transmitting terminal can transfer a file; inquiring each receiving terminal server corresponding to each target receiving terminal whether to receive the file; verifying whether each target receiving terminal can receive the file; inquiring each target receiving terminal whether to receive the file; transmitting to the transmitting terminal server the reply of receiving terminals to receive the file; creating a list of determined receiving terminals; requesting the transmitting terminal to transfer the file; receiving the file from the transmitting terminal; and transferring the file to each receiving terminal server corresponding to the determined receiving terminals or to each determined receiving terminal.

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: 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 data synchronization system is provided. In the data synchronization system, a synchronization message transmitting party transmits a synchronization message with meta information to a synchronization message receiving party, and the synchronization message receiving party interprets and stores the meta information included in the synchronization message, and performs further processing for data that is to be synchronized, according to the meta information. Therefore, the frequency of wireless connections for synchronization is minimized.

Abstract: A method for importing Digital Rights Management (DRM) data converts non-Open Mobile Alliance (OMA) DRM data to OMA DRM data for a user domain in DRM solutions. The method includes registering a local rights manager (LRM) to a domain authority or a Rights Issuer and exchanging user domain information, and creating a DRM content format (DCF) and a rights object (RO) that conform to Open Mobile Alliance (OMA) DRM standard from non-OMA DRM data based on the user domain information. A method for using DRM data includes registering the LRM, creating DCF conforming to OMA DRM standard from non-OMA DRM data, creating an RO, and transferring the DCF and RO to a DRM agent of a device.

Abstract: A method for registering a Domain Authority (DA) and a Rights Issuer (RI) for Digital Rights Management includes exchanging information between the DA and the RI. The DA and RI are registered by the exchanging of information before executing other protocol, and the method for registering can be incorporated into the following methods for implementing Digital Rights Management (DRM) with Secure Content Exchange features: (1) acquiring user domain Rights Objects (RO) by a DRM agent; (2) using the user domain RO by a 2.0 DRM agent; and (3) using imported user domain RO by a 2.0 DRM agent.

Abstract: A method and apparatus for normalizing a histogram utilizing a backward cumulative histogram which can cumulate a probability distribution function in an order from a greatest to smallest value so as to estimate a noise robust histogram. A method of normalizing a speech feature vector includes: extracting the speech feature vector from a speech signal; calculating a probability distribution function using the extracted speech feature vector; calculating a backward cumulative distribution function by cumulating the probability distribution function in an order from a largest to smallest value; and normalizing a histogram using the backward cumulative distribution function.

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.