APPARATUS AND METHOD FOR SPEECH DETECTION USING VOICED CHARACTERISTICS OF HUMAN SPEECH

摘要

A method for distinguishing the voice by using the voiced sound features of the human voice and an apparatus therefor are provided to overcome a problem that the performance of the existing voice and non-voice determining techniques is degraded in the actual noise environment. An input signal sound-quality enhancing part(201) removes additional noise from a sound signal including a voice signal and noise signal to minimize the phenomenon that the sound quality of the input signal is degraded by the additional noise. A voiced sound feature detecting part(205) extracts voiced sound features based on the voice signal received from the sound-quality enhancing part. A voiced sound/unvoiced sound determining model part(207) stores the threshold value or critical value of the voiced sound features extracted from a pure voice model in which the noise is not included. A voiced sound/unvoiced sound determining unit(209) compares 11 voiced sound features extracted by the voiced sound feature detecting part with the stored threshold value or critical value.