Spectral Normalization for Speaker-Invariant Feature Extraction

화자 불변 특징추출을 위한 스펙트럼 정규화

We present a new method to normalize spectral variations of different speakers based on physiological studies of hearing. The proposed method uses the cochlear frequency map to warp the input speech spectra by interpolation or decimation. Using this normalization method, we can obtain much improved recognition results for speaker independent speech recognition.