Abstract: A display apparatus and a method for executing a link and a method for recognizing a voice thereof are provided. The method for executing a link of the display apparatus includes displaying a user interface, determining a text included in a link included in the user interface, displaying the text determined in the link to be distinguished from other texts, recognizing a voice input from a user, and if the voice uttered by the user matches the text determined in the link, executing the link associated with the matching text. Accordingly, possibility of misrecognition of a voice input by the user is reduced, and the user controls a display apparatus using more exact voice recognition.

Abstract: Provided are a real-time face recognition-based selective recording apparatus and method. The apparatus includes a face recognition unit which recognizes a face of a person in a decompressed input image frame; a recording position setting unit which sets one of an image frame in which the person appears and a scene change start frame including the image frame as a valid recording point if the recognized face is detected for a predetermined period of time or detected a predetermined number of times, and identifies a position, which corresponds to a set image frame, in an image compression stream; and a recording unit which records the image compression stream from the identified position and storing the recorded image compression stream in real time.

Abstract: A speaker adaptation method and apparatus are provided including extracting adapted data from speech recognition data stored in a database, and modifying a sound model by using a speaker adaptation method selected based on a type of the extracted adapted data.

Abstract: An apparatus and method for optimizing a concatenate recognition unit are provided. The apparatus and method of optimizing a concatenate recognition unit may generate an optimized concatenate recognition unit based on a basic language model generated using the concatenate recognition unit extracted from statistical information.

Abstract: Provided are a real-time face recognition-based selective recording apparatus and method. The apparatus includes a face recognition unit which recognizes a face of a person in a decompressed input image frame; a recording position setting unit which sets one of an image frame in which the person appears and a scene change start frame including the image frame as a valid recording point if the recognized face is detected for a predetermined period of time or detected a predetermined number of times, and identifies a position, which corresponds to a set image frame, in an image compression stream; and a recording unit which records the image compression stream from the identified position and storing the recorded image compression stream in real time.