To assess the performance of the system, we used sensitivity and specificity. Using the HTK classifiers, the classification is carried out on two pathological databases, Massachusetts Eye and Ear Infirmary (MEEI) and Saarbruecken Voice Database (SVD). In this study, we used a variation of HFCC called Equivalent Rectangular Bandwidth (ERB) to study the effects of HFCC on the classification of pathological voices. These parameters are introduced and calculated in every frame. Among these tools are the Human Factor Cepstral Coefficients (HFCC) combined with prosodic parameters, the Noise-Harmonic Ratio (NHR), the Harmonic-Noise Ratio (HNR), analysis of trend Fluctuations (DFA) and Fundamental frequency (F0). In this context, several tools have been introduced to achieve early detection of voice disorders.
These automatic systems can help clinicians customize and detect the existence of any vocal pathology.
It is for these reasons that it is very necessary to implement systems for detecting and classifying vocal pathologies. So, any alteration of the voice can prevent the person from exercising his professional and daily life naturally. Natural sounding Text-to-Speech voices by Cepstral (Natural sounding computer voices) and SpeakComputer free Text-to-Speech software readers, together can read. The company primarily produces synthetic voices to be used in telephony systems, mobile applications, desktop applications, and with other TTS software such as. It is characterized by its great ability to transmit our ideas, our emotions, our personality etc.
Human speech is a means of communication that is very important in our daily lives.
0 kommentar(er)
