Exploration of temporal dynamics of frequency domain linear prediction cepstral coefficients for dialect classification

Abstract

Speakers exhibit dialectal traits in speech at sub-segmental, segmental, and supra-segmental levels. Any feature representation for dialect classification should appropriately represent these dialectal traits. Traditional segmental features such as mel-frequency cepstral coefficients (MFCCs) fail to represent sub-segmental and supra-segmental dialectal traits. This study proposes to use frequency domain linear prediction cepstral coefficients (FDLPCCs) for dialect classification inspired by its long temporal summarization during pole estimation. The i-vectors and x-vectors derived from both baseline (MFCCs, linear prediction cepstral coefficients (LPCCs), perceptual LPCCs (PLPCCs), RASTA filtered PLPCCs (PLPCC-R) and proposed (FDLPCC) features are used for identifying the dialects with support vector machine (SVM) and feed-forward neural network (FFNN) as classifiers. Proposed FDLPCC features have shown to perform better than baseline features such as MFCCs and PLPCC-Rs (best among LPCCs variants) by an absolute improvement of 3.4% and 3.9% (in unweighted average recall (UAR)), with i-vector + SVM system and 1.6% and 4.6% (in UAR), i-vector + FFNN system respectively. It is also found that there exists a complementary information between the proposed and baseline features. Furthermore current studies are compared with previous studies and it is found that performances of current studies are better than previous studies.