Abstract: In a speech recognition method, at least two standard feature vector series having different signal-to-noise ratios (SNRs) are prepared in advance for each category. Then, an SNR is calculated from an input speech signal, and a noise adaptive standard feature vector series is calculated by a linear interpolation method between the prepared standard feature vector series using the calculated SNR. Finally, a dynamic programming matching operation is performed upon the feature vectors of the noise adaptive standard feature vector series and the feature vectors of the input speech signal.