a parallel hybrid system of hmm and gmm modeling techniques was implemented and used in a telephony speaker verification and identification system. spectral subtraction and weighted projection measure were used to render this system more robust against additional noise. cepstral mean subtraction method was also applied for the compensation of convolution noise due to transmission channel degrad...

This paper presents new results by using our recently proposed on-line Bayesian learning approach for affine transformation parameter estimation in speaker adaptation. The on-line Bayesian learning technique allows updating parameter estimates after each utterance and i t can accommodate flexible forms of transformation functions as well as prior probability density function. We show through ex...

We present a new method of Speaker Adapted Training (SAT) that is more robust, faster, and results in lower error rate than the previous methods. The method, called Inverse Transform SAT (ITSAT) is based on removing the differences between speakers before training, rather than modeling the differences during training. We develop several methods to avoid the problems associated with inverting th...

Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.

A method is proposed to model the interspeaker variability of formant patterns for oral vowels. It is assumed that this variability originates in the differences existing among speakers in the respective lengths of their front and back vocal-tract cavities. In order to characterize, from the spectral description of the acoustic speech signal, these vocal-tract differences between speakers, each...

The performance of telephone-based speaker verification systems can be severely degraded by linear and non-linear acoustic distortion caused by telephone handsets. This paper proposes to combine a handset selector with stochastic feature transformation to reduce the distortion. Specifically, a GMMbased handset selector is trained to identify the most likely handset used by the claimants, and th...

We present a new method of Speaker Adapted Training (SAT) that is more robust, faster, and results in lower error rate than the previous methods. The method, called Inverse Transform SAT (ITSAT) is based on removing the di erences between speakers before training, rather than modeling the di erences during training. We develop several methods to avoid the problems associated with inverting the ...

This paper proposes normalisation methods based on fuzzy set theory for speaker veri cation. A claimed speaker's score used to accept or reject this speaker is viewed as a fuzzy membership function. We propose two scores: the fuzzy entropy and fuzzy C-means membership functions. Moreover, a likelihood transformation is considered to obtain a general approach and, based on this, ve more fuzzy sc...

We propose an improved maximum a posteriori (MAP) learning algorithm of continuous-density hidden Markov model (CDHMM) parameters for speaker adaptation. The algorithm is developed by sequentially combining three adaptation approaches. First, the clusters of speaker-independent HMM parameters are locally transformed through a group of transformation functions. Then, the transformed HMM paramete...