Apparatus and method of voice recognition system for AV system

A voice recognition system for an audio-visual (AV) system generating an audio, the voice recognition system comprising:

• a reflected sound remover having a plurality of filters, the reflected sound remover being configured to receive an input sound signal including a reflected AV system audio, a user's voice, and a noise, and being configured to remove the reflected audio from the input sound according to user's voice information;
• a voice detector configured to detect the user's voice from a signal outputted from the reflected sound remover and to obtain the user's voice information based on the detected user's voice;
• and
• a voice recognition unit configured to compare the detected user's voice with voice patterns that belong to at least one model, wherein the reflected sound remover comprises:
• a first filter bank dividing the original AV system audio into a first plurality of signals having different frequency ranges;
• a second filter bank dividing the input sound into a second plurality of signals having the different frequency ranges;
• a plurality of adaptive filters removing the reflected AV system audio from the second plurality of signals using the first plurality of signals;
• a third filter bank combining the signals outputted from the plurality of adaptive filters;
• wherein the plurality of adaptive filters are configured to determine whether or not to adapt according to the voice detector detecting a beginning and an end of the user's voice;
• and
• wherein when the starting point of the user's voice is determined, the adaptive filter unit stops adapting, but it restarts adapting when the ending point of the user's voice is determined.