“…The MFCCs, despite the limitations of the Mel filterbank, are the most widely used features for most speech processing applications like speech recognition ( Deller et al, 1993 ), speaker verification ( Sahidullah and Saha, 2013 ), emotion recognition ( Ooi et al, 2014;Zheng et al, 2014;Reyes-Vargas et al, 2013;Ververidis and Kotropoulos, 2006 ), language recognition ( Huang et al, 2013 ), etc., and even for non-speech acoustic signal processing tasks, such as music information retrieval ( Qin et al, 2013 ). However, as discussed in the preceding subsection, it is quite ambitious to assume that they would provide the best possible performance for all applications.…”