Speaker gender recognition using score level fusion by AdaBoost
Masatsugu Ichinof, Naohisa Komatsuff, Wang Jian-Gangfff, Yau Wei Yunffj · 2010
We propose speaker gender recognition achieved by using score level fusion by AdaBoost. Soft biometrics has been focused on because recognition by fusing biométrie systems and soft biométrie traits may improve the accuracy of recognition and decrease the time for this. Gender recognition is important for speaker recognition and can provide important information to speaker recognition systems. Mel-frequency cepstral coefficient (MFCC) and pitch contain gender information. MFCCs and pitch are often used for gender recognition. Consequently, identification accuracy may be improved by using both MFCC and pitch. We focused on the score level fusion to accomplish speaker gender recognition. We propose speaker gender recognition based on the score level fusion using AdaBoost because it can control the recognition accuracy and recognition time. We experimentally demonstrate the proposed method's effectiveness through simulation results and show that it achieves greater accuracy than that obtained by using single information from voice.