Text-Independent Emirati-Accented Speaker Identification in Emotional Talking Environment
Ismail Mohd Adnan Shahin · 2018
This work is devoted to enhancing text-independent Emirati-accented “speaker identification performance in emotional talking environment” based on “First-Order Hidden Markov Models (HMM1s), Second-Order Hidden Markov Models (HMM2s), and Third-Order Hidden Markov Models (HMM3s)” as classifiers. In this research, our database was captured from fifty Emirati native speakers (twenty five per gender) uttering eight common Emirati sentences in each of neutral, angry, sad, happy, disgust, and fear emotions. The extracted features of our collected database are called “Mel-Frequency Cepstral Coefficients (MFCCs)”. Our results show that average Emirati-accented “speaker identification performance in emotional environment” is 58.8%, 61.8%, and 65.9% based on HMM1s, HMM2s, and HMM3s, respectively. The attained “average speaker identification performance in emotional environment based on HMM3s” is very close to that obtained in “subjective assessment by human listeners”.