Title :
Performance evaluation and improvement of speaker recognition over GSM environment
Author :
Tan, Tan-Hsu ; Chang, Shih-Wei ; Yang, Chung-Ho
Author_Institution :
Dept. of Electr. Eng., Nat. Taipei Univ. of Technol., Taiwan
Abstract :
Performance evaluation and improvement of speaker recognition over real GSM environment are investigated. A text-independent speaker recognition system based on Gaussian mixture model (GMM) is implemented for performance evaluation. To match the real-world conditions, an NTUT-LAB416 speech corpus is collected over GSM telecommunication network from in-car environment of various driving speeds. An approach employing multistyle training model is proposed to alleviate the adverse effects due to environmental mismatch. Also, a post-processing scheme using auto-regression and moving-average (ARMA) filter is suggested to overcome the varying noise conditions. Experimental results indicate that the proposed approaches can effectively improve the performance of speaker recognition over GSM environment.
Keywords :
Gaussian processes; autoregressive moving average processes; cellular radio; filtering theory; performance evaluation; signal denoising; speaker recognition; GSM telecommunication network; Gaussian mixture model; NTUT-LAB416 speech corpus; auto-regression moving-average filter; driving speeds; in-car environment; multistyle training model; performance evaluation; performance improvement; real GSM environment; text-independent speaker recognition system; Automatic speech recognition; Business; Data security; Engines; Filters; GSM; Mobile handsets; NIST; Speaker recognition; Working environment noise;
Conference_Titel :
Security Technology, 2003. Proceedings. IEEE 37th Annual 2003 International Carnahan Conference on
Print_ISBN :
0-7803-7882-2
DOI :
10.1109/CCST.2003.1297600
