| The speaker verification problem can be stated as follows: given two speech recordings, determine whether or not they have been uttered by the same speaker. Most current speaker verification systems are based on Gaussian mixture models. This probabilistic representation allows to adequately model the complex distribution of the speech frames. It however represents an inadequate basis for discriminating between speakers, which is the key issue in the area of speaker verification. In the first part of this thesis, we attempt to overcome these difficulties by proposing to combine support vector machines with two generative approaches based on Gaussian mixture models. In the second part of this thesis, we present a new approach to modeling the speaker's long-term prosodic and spectral characteristics. This novel approach is based on continuous approximations of the prosodic and cepstral contours. Finally, we perform a scores fusion between systems based on long- and short-term speaker features. |
