Date of Graduation
Statler College of Engineering and Mineral Resources
Lane Department of Computer Science and Electrical Engineering
This research presents new text-independent speaker recognition system with multivariate tools such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA) embedded into the recognition system after the feature extraction step. The proposed approach evaluates the performance of such a recognition system when trained and used in clean and noisy environments. Additive white Gaussian noise and convolutive noise are added. Experiments were carried out to investigate the robust ability of PCA and ICA using the designed approach. The application of ICA improved the performance of the speaker recognition model when compared to PCA. Experimental results show that use of ICA enabled extraction of higher order statistics thereby capturing speaker dependent statistical cues in a text-independent recognition system. The results show that ICA has a better de-correlation and dimension reduction property than PCA. To simulate a multi environment system, we trained our model such that every time a new speech signal was read, it was contaminated with different types of noises and stored in the database. Results also show that ICA outperforms PCA under adverse environments. This is verified by computing recognition accuracy rates obtained when the designed system was tested for different train and test SNR conditions with additive white Gaussian noise and test delay conditions with echo effect.
Gangisetty, Smitha, "Text-independent speaker recognition" (2005). Graduate Theses, Dissertations, and Problem Reports. 1596.