Speaker identification through use of features selectedusing genetic algorithm

On the Use of Different Speech Representations for Speaker Modeling

“…Such methods include feature selection, feature transformation, and novel speech representations alternative to a spectral representation. By feature selection, one attempts to discover a subset of features likely carrying speaker-specific information (less associated with linguistic information reciprocally) from a common spectral representation [19], [24], [34]. Apart from some text-dependent cases [24], [34], however, most such fail to generate a proper subset due to the lack of an appropriate mathematical expression methodology [5] and numberless varieties of speaker-specific information.…”

Wavelet LPC with Neural Network for Spoken Arabic Digits Recognition System

“…Ganchev [39][40][41][42][43] proposed PNN with Mel-frequency cepstral coefficients for textindependence. Although there are numerous enhanced versions of the original PNN presented by many researchers, which are either more economical or exhibit an appreciably better performance for simplicity of exposition, we adopted and invoked the original PNN for classification task (see Fig.…”

Speaker identification based on the frame linear predictive coding spectrum technique

“…However, these techniques are unsuitable for speaker identification because they accept stationary signal within a given time frame and may therefore lack the ability to analyze the nonstationary signals or signals in transient state (Avci & Akpolat, 2006). Therefore, many algorithms were developed to find a better representation of a speaker, for example: linear predictive coding (LPC) technique (Adami & Barone, 2001;Haydar, Demirekler, & Yurtseven, 1998;Wutiwiwatchai, Achariyakulporn, & Tanprasert, 1999), Mel frequency cepstral coefficient (MFCC) (Mashao & Skosan, 2006;Sroka & Braida, 2005) and wavelet (Lung, 2006;Wu & Lin, 2009;Wu & Ye, 2009). In this paper, an improved method based on LPC is proposed.…”