Pi-sigma and hidden control based self-structuring models for text-independent speaker recognition

Two text-independent speaker recognition methods based on self-structuring hidden control (SHC) neural models and self-structuring pi-sigma (SPS) neural models are proposed. The authors have designed the self-structuring models to achieve better model structures, i.e., data determined architectures instead of a priori determined architectures. PS and HC neural models for speaker recognition are also proposed. Each of the four methods requires typically 75% fewer neural models compared with the predictive neural network based text-independent speaker recognition method, i.e., the latter contains an ergodic M-state model using M neural models (M=4) for each speaker; here, each of the speaker recognition systems uses only one neural model to realize an ergodic M-state model. The pi-sigma models have been modified to obtain self-structuring PS models and the speech recognition SHC models have been changed to fit into speaker recognition systems.<>