Dysphonia discovering using a Goertzel algorithm implementation for vocal signals analysis

Background and objectives: The identification, study and classification of anomalies in vocal signals are used to support physicians in the diagnosis and monitoring of vocal robe pathologies. Dysphonia is the most common disorder causing difficulties in voice production. Dysphonia refers to any impairment in voice quality, and significantly impacts on the quality of life. Early detection is imperative to prevent severe pathologies or to early detect chronic ones. Voice signal processing techniques, such as Fast Fourier Transform (FFT) and Praat, are noninvasive tools used to study phonatory apparatus diseases. Nevertheless there is room for improving efficacy in vocal signal patterns identification that could be related to vocal robe related pathologies. Methods: The focus is on the possibility of using Goertzel Algorithm (GA) characteristics to improve state of the art for pattern identification in vocal signals. A tool for early identification of dysphonia based on GA is presented. An optimized version of GA, able to detect voice frequency anomalies has been implemented. Results: The proposed tool has been tested with vocal signal datasets containing both normophonic and pathological subjects. The results are reported in terms of different implementation strategies and techniques. Experimental tests were performed comparing GA based and FFT based signal analysis tools in terms of: (i) efficiency and (ii) capacity of features identification. Performance parameters report: (i) an efficiency in terms of processing time improved by 37 % (i.e. 16.78 ms for FFT vs 12.26 ms for GA) and memory requirements reduced by 74 %; (ii) GA enabled the identification of healthy and pathological conditions better than FFT with a significance level below 0.05. Conclusions: Results of using GA-based method on vocal signal processing, compared with existing methods, demonstrate the reliability of the proposed method in early identification of dysphonia and in clinical monitoring of patients post treatment.