Alternatively, laryngoscopic techniques such as direct laryngoscopy, indirect laryngoscopy, and telescopic video laryngoscopy are invasive tools which allow the observation of vocal folds. Moreover, this subjective evaluation can cause inconsistency on judging pathological voice quality. Auditory-perceptual evaluation of voice quality is subjective because of the variability between listeners. For this approach, voice evaluation is performed subjectively by the clinician’s direct audition. Auditory-perceptual evaluation offers a standardized procedure for assessment of abnormal voice quality.
For this approach, the severity (degree) and quality of dysphonia are evaluated by a tool such as GRBAS (Grade, Roughness, Breathiness, Asthenia, and Strain) scale. In clinical practice, the primary approach to assess voice quality is the auditory-perceptual evaluation. Introductionĭisordered voice quality could be a symptom of a disease related to laryngeal disorders. The multitaper MFCC features may be helpful in identifying voices at risk for a real pathology that has to be proven later. The results demonstrate that adapted weighted Thomson multitaper method could distinguish between normal voice and disordered voice better than the results done by the conventional single-taper (Hamming window) technique and two newly proposed windowing methods. We also compare their performance by newly proposed windowing techniques and conventional single-taper technique. This study shows investigations on reducing variance for the classification of two different voice qualities (normal voice and disordered voice) using multitaper MFCC features. However, MFCC features are usually calculated from a single window (taper) characterized by large variance.
The Mel Frequency Cepstral Coefficients (MFCCs) are widely used in order to extract essential information from a voice signal and became a popular feature extractor used in audio processing.
0 kommentar(er)
