Precise reconstruction of the mucosal wave for voice pathology detection and characterization

Voice recordings are the only basis for pathology detection and classification in critical cases where invasive instrumentation is not possible as in new-borns and long-distance screening, among others. Classical pathology detection methods using voice rely on processing basic information from the voice signal, as the pitch, jitter, shimmer, HNR and others similar. In the present work a new method to estimate HNR from the detection and processing of a signal correlate of the mucosal wave is presented, as it is well known that mucosal wave alterations give clues to the presence of certain pathologies. An evaluation of mucosal wave in recordings from normal and pathological cases is presented and discussed, checking the results against those produced from simulated voice by a 2-mass model.