On the use of complementary spectral features for speaker recognition

Abstract

The most popular features for speaker recognition are Mel frequency cepstral coefficients (MFCCs)and linear prediction cepstral coefficients (LPCCs). These features are used extensively because theycharacterize the vocal tract configuration which is known to be highly speaker-dependent. In this work,several features are introduced that can characterize the vocal system in order to complement thetraditional features and produce better speaker recognition models. The spectral centroid (SC), spectralbandwidth (SBW), spectral band energy (SBE), spectral crest factor (SCF), spectral flatness measure(SFM), Shannon entropy (SE), and Renyi entropy (RE) were utilized for this purpose. This workdemonstrates that these features are robust in noisy conditions by simulating some common distortionsthat are found in the speakers environment and a typical telephone channel. Babble noise, additivewhite Gaussian noise (AWGN), and a bandpass channel with 1 dB of ripple were used to simulate these noisy conditions. The results show significant improvements in classification performance for all noiseconditions when these features were used to complement the MFCC and MFCC features. In particular, the SC and SCF improved performance in almost all noise conditions within the examined SNR range (10-40 dB). For example, in cases where there was only one source of distortion, classification improvements of up to 8 and 10 were achieved under babble noise and AWGN, respectively, using the SCF feature.