Article: Fusion features for robust speaker identification Journal: International Journal of Signal and Imaging Systems Engineering (IJSISE) 2018 Vol.11 No.2 pp.65 - 72 Abstract: Speaker's identification systems aim to identify, through a set of speech parameters, the speaker's identity. Thus, a relevant speech representation is required. For this purpose, we suggest to combine spectral parameters as the Mel frequency Cepstral coefficients (MFCC) and the perceptual linear predictive (PLP) coefficients and prosodic parameter such as the signal fundamental frequency (F0). There are two main classes for F0 estimation divided into temporal and spectral methods. We employ the sawtooth waveform inspired pitch estimator (SWIPE) algorithm for F0 estimation. It is based on the pitch estimation in the frequency domain. In addition, we evaluate the Gaussian mixture model-universal background model (GMM-UBM) for the modelling purpose. Experiments are involved in Timit database. Identification rates are promising and prove the benefit of the combination for MFCC and PLP rather than using each feature separately and this mainly for noisy data. Inderscience Publishers - linking academia, business and industry through research

Title: Fusion features for robust speaker identification

Authors: Ines Ben Fredj; Youssef Zouhir; Kaïs Ouni

Addresses: Research Unit Signals and Mechatronic Systems SMS, UR13ES49, National Engineering School of Carthage, Carthage University, Tunis, 2035, Tunisia ' Research Unit Signals and Mechatronic Systems SMS, UR13ES49, National Engineering School of Carthage, Carthage University, Tunis, 2035, Tunisia ' Research Unit Signals and Mechatronic Systems SMS, UR13ES49, National Engineering School of Carthage, Carthage University, Tunis, 2035, Tunisia

Abstract: Speaker's identification systems aim to identify, through a set of speech parameters, the speaker's identity. Thus, a relevant speech representation is required. For this purpose, we suggest to combine spectral parameters as the Mel frequency Cepstral coefficients (MFCC) and the perceptual linear predictive (PLP) coefficients and prosodic parameter such as the signal fundamental frequency (F0). There are two main classes for F0 estimation divided into temporal and spectral methods. We employ the sawtooth waveform inspired pitch estimator (SWIPE) algorithm for F0 estimation. It is based on the pitch estimation in the frequency domain. In addition, we evaluate the Gaussian mixture model-universal background model (GMM-UBM) for the modelling purpose. Experiments are involved in Timit database. Identification rates are promising and prove the benefit of the combination for MFCC and PLP rather than using each feature separately and this mainly for noisy data.

Keywords: robust speaker identification; Gaussian mixture model-universal background model; GMM-UBM; fusion features; fundamental frequency; sawtooth waveform inspired pitch estimator; SWIPE; Mel frequency Cepstral coefficients; MFCC; perceptual linear predictive; PLP; Timit.

DOI: 10.1504/IJSISE.2018.091881

International Journal of Signal and Imaging Systems Engineering, 2018 Vol.11 No.2, pp.65 - 72

Received: 18 Apr 2017
Accepted: 08 Oct 2017
Published online: 20 May 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Fusion features for robust speaker identification

Keep up-to-date