Singer identification is essential in music retrieval, for the performance of singer identification system can be severely degraded by the interference of background music.

Feature extraction of speaker recognition system based on mathematical morphological filtering;

Text-independent speaker recognition based on recurring expectation maximum adjustment algorithm;

Research on the discriminating value of different frequency formants in speaker recognition

Study on Speaker Identification System Based on Gaussian Mixture Model;

The performance of speaker verification systems is often compromised under real-world environments.

Real-time speaker verification in telephone communication environment has great challenge and practical usage, because the effectual signal collect multiplexing in real telephone network need to be efficient and accurate, and the effectual voice should be distinguished from the silence, circuitry noise and sudden noise when the voices are still being recorded.