Robust FHPD Features from Speech Harmonic Analysis for Speaker Identification

Speaker identification accuracy decreases significantly in the presence of additive noise. In this paper, we propose a robust speech feature extraction method, which is based on the harmonic structure of voiced segments. The robust features are composed of fundamental and harmonic peak data from short-time spectrum. These features are evaluated by thirty speaker data from TIMIT database and additive noise signals from NOISEX-92 database with clean training and noisy testing samples. Results reflect that under low SNR (signal-to-noise ratio) environments new features achieve better performance than conventional MFCC (Mel-Frequency Cepstral Coefficients) parameters.