Mobile App Based Feature Extraction of a Speech Signal

Abstract

Mobile phones are very much prevalent in today?s generation. They can be utilized in the diagnosis and treatment of many diseases. The traditional methods which are used for the diagnosis of the vocal cord disorder are usually invasive, expensive and slow. Sometimes, they are also annoying. So the purpose of this paper is to design a non-invasive technique for the feature extraction of speech signal which can later be used for the vocal cord disorder diagnosis which would be cheaper, faster and repeatable. This paper summarizes a study of the mobile app based technique used to extract features of a speech signal with an ultimate aim to discriminate and detect vocal cord disorder. The study is concentrated in the analysis of relevance of a set of features obtained from the analysis of phonated speech, specifically an open vowel as \a\. The features which are extracted for the mobile app are frequency, pitch, amplitude and jitter.