A method and apparatus for speech detection

摘要

The speech detection apparatus of the present invention comprises: a reference model maker for extracting a plurality of parameters for a speech detection from training data, and making a reference model based on the parameters; a parameter extractor for extracting the plurality of parameters from each frame of an input audio signal; and a decision device for deciding whether the audio signal is speech or not, by comparing the parameters extracted from the input audio signal with the reference model. The reference model maker makes the reference model for each phonemes. The decision device includes: a similarity computing unit for comparing the parameters extracted from each frame of the input audio signal with the reference model, and computing a similarity of the frame with respect to the reference model; a phoneme decision unit for deciding a phoneme of each frame of the input audio signal based on the similarity computed for each phoneme; and a final decision unit for deciding whether a specific period of the input audio signal including a plurality of frames is speech or not based on the result of the phoneme decision. <IMAGE>