Language Recognition Using Tim-Frequency Principal Component analysis and Acoustic Modeling

摘要

Time-Frequency Principal Component (TFPC) is a speech parameterization technique based on a principal component analysis applied to acoustic feature parameters augmented by their time context. In this paper, we investigate on the performance of TFPC in the framewrok of automatic language recognition. In our experimetns, identification rate is improved compared to the use of the conventional cepstral coefficients augmented by their #DELTA# coefficients.