Detection of possibility of Laryngeal Cancer through Mel Frequency Cepstrum Coefficient Analysis

Laryngeal Cancer is a condition in which cancerous cells are formed in larynx. Notable symptoms are hoarseness in the voice, sore throat, trouble or pain while swallowing and ear pain. The detection of the modification in voice through Acoustic analysis can serve as a complement to other medical procedures. The novelty of the paper lies in utilizing Mel Frequency Cepstrum Coefficients (MFCC) for detection of Laryngeal cancer. This method for detection of laryngeal cancer was not researched, traditionally the detection of Laryngeal cancer was only possible through clinical examination. In the proposed method, the analysis is carried out by comparing the coefficients of voices of patient affected by Laryngeal Cancer to that of normal human voice. The study involves conversion of voice signal to parametric representation. On further processing, it was observed that there was significant deviation in the vital coefficients of cancerous voice as compared to that of normal voice and the initial results show that the possibility of detection was found to be 100% in a dataset comprising of 60 samples.

[1]  Shanq-Jang Ruan,et al.  FPGA implementation of automatic speech recognition system in a car environment , 2015, 2015 IEEE 4th Global Conference on Consumer Electronics (GCCE).

[2]  Kamil Ismaila Adeniyi,et al.  Comparative Study on the Performance of Mel-Frequency Cepstral Coefficients and Linear Prediction Cepstral Coefficients under different Speaker's Conditions , 2014 .

[3]  Rohilah Sahak,et al.  Mel-frequency cepstrum coefficient analysis of infant cry with hypothyroidism , 2009, 2009 5th International Colloquium on Signal Processing & Its Applications.

[4]  T. Ananthakrishna,et al.  Vocal Fold Pathology Assessment Using Mel-Frequency Cepstral Coefficients and Linear Predictive Cepstral Coefficients Features , 2014 .

[5]  Ahmed Hammouch,et al.  Phonocardiogram classification based on MFCC extraction , 2017, 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA).

[6]  V. D. Dighore,et al.  Analysis of Asthma by using Mel frequency cepstral coefficient , 2016, 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT).

[7]  Yuan Xue,et al.  Matlab-Based Intelligent Voiceprint Recognition System , 2016, 2016 Sixth International Conference on Instrumentation & Measurement, Computer, Communication and Control (IMCCC).

[8]  Adnane Cherif,et al.  Speech recognition system based on short-term cepstral parameters, feature reduction method and Artificial Neural Networks , 2016, 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[9]  Shufang Zhang,et al.  Design of audio signal processing and display system based on SoC , 2015, 2015 4th International Conference on Computer Science and Network Technology (ICCSNT).