A Robust Speaker Identification Using Optimized Confidence and Modified HMM Decoder

최적화된 관측 신뢰도와 변형된 HMM 디코더를 이용한 잡음에 강인한 화자식별 시스템

Speech signal is distorted by channel characteristics or additive noise and then the performances of speaker or speech recognition are severely degraded. To cope with the noise problem, we propose a modified HMM decoder algorithm using SNR-based observation confidence, which was successfully applied for GMM in speaker identification task. The modification is done by weighting observation probabilities with reliability values obtained from SNR. Also, we apply PSO (particle swarm optimization) method to the confidence function for maximizing the speaker identification performance. To evaluate our proposed method, we used the ETRI database for speaker recognition. The experimental results showed that the performance was definitely enhanced with the modified HMM decoder algorithm.