Improving Speaker Identification Performance Under the Shouted Talking Condition Using the Second-Order Hidden Markov Models

Speaker identification systems perform well under the neutral talking condition; however, they suffer sharp degradation under the shouted talking condition. In this paper, the second-order hidden Markov models (HMM2s) have been used to improve the recognition performance of isolated-word text-dependent speaker identification systems under the shouted talking condition. Our results show that HMM2s significantly improve the speaker identification performance compared to the first-order hidden Markovmodels (HMM1s). The average speaker identification performance under the shouted talking condition based onHMM1s is 23%. On the other hand, the average speaker identification performance based on HMM2s is 59%.