Emirati Speaker Verification Based on HMM1s, HMM2s, and HMM3s
This is an incremental improvement for Emirati speaker verification systems, addressing a domain-specific problem.
The paper tackled speaker verification for Emirati speakers by comparing first-, second-, and third-order Hidden Markov Models (HMMs), finding that HMM3s outperformed the others and achieved results close to human subjective assessment.
This work focuses on Emirati speaker verification systems in neutral talking environments based on each of First-Order Hidden Markov Models (HMM1s), Second-Order Hidden Markov Models (HMM2s), and Third-Order Hidden Markov Models (HMM3s) as classifiers. These systems have been evaluated on our collected Emirati speech database which is comprised of 25 male and 25 female Emirati speakers using Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features. Our results show that HMM3s outperform each of HMM1s and HMM2s for a text-independent Emirati speaker verification. The obtained results based on HMM3s are close to those achieved in subjective assessment by human listeners.