LPC, LPCC and MFCC parameterisation applied to the detection of voice impairments

There is an increased risk for vocal and voice diseases due to the modern way of life. It is well known that most of the vocal and voice diseases cause changes in the acoustic voice signal. These diseases have to be diagnosed and treated during an early stage. Acoustic analysis is a non-invasive technique based on digital processing of speech signal. Acoustic analysis can be a useful tool to diagnose this kind of diseases, furthermore it presents several advantages: it is a non-invasive tool, an objective diagnostic and, also, it can be used for the evaluation of surgical and pharmacological treatments and rehabilitation processes. ENT clinicians use acoustic voice analysis to characterise pathological voices. In this paper, we study threee well known parameterisation approaches applied to the automatic detection of voice disorders. Former and actual works demonstrate that impaired voice detection can be carried out by means of supervised neural nets: MLP (Multilayer perceptron). We have focused our task in detection of impaired voices by means of neural network technology (ANN) and parameters such a LPC, LPCC and MFCC extracted from the voice signal. The performance of the neural network based detector is compared with that using acoustic parameters such a Fo, NHR, NNE, Shimmer, Jitter... as input variables. The aim of this paper is to study and compare those widely used parameterisation method in speech technology applied to the detection of impaired voices.