Speaker identification investigation and analysis in Two distinct emotional talking environments

摘要

The focus of this work is to investigate and analyze speaker identification in two different emotional talking environments based on a well-known classifier called Hidden Markov Models (HMMs). The first talking environment is unbiased towards any emotional state, while the second one is biased towards different emotional states. Each talking environment is comprised of six distinct emotions. The six emotions are neutral, angry, sad, happy, disgust, and fear. Our investigation and analysis in this work show that speaker identification performance in the second talking environment is superior to that in the first one. The results achieved in the current work are close to those obtained in subjective assessment by human judges.