Objective characterization of oesophageal voice supporting medical diagnosis, rehabilitation and monitoring

摘要: Otolaryngologists use computational tools in the objective diagnosis of vocal folds pathologies by means a set acoustic parameters among others. This can be achieved cases slight pathologies, but it does not exist any commercial software suitable for severe degradations speech, as they are oesophageal voice laryngectomees. The present article shows high-accuracy algorithm detection periodicity cycles both and laryngeal voices with low quality which allows accurate automatic estimation pitch, jitter shimmer. As proposed works also slighter is useful contribution doctors to perform an control during rehabilitation monitoring stages. Thus, patient controlled learning stage saved medical record results parameters' measurements order detect possible relapses.