On the prediction of speech quality ratings of tracheoesophageal speech using an auditory model

Total laryngectomy is often the treatment of choice for many patients suffering from laryngeal cancer. This procedure alters the speech production mechanism, and tracheoesophageal (TE) speech is an alternative where the pulmonary air is forced through the esophagus. TE speech is often characterized by poor intelligibility and voice quality. Acoustic analysis of TE speech has the potential of quantifying the voice quality and assisting the speech pathologist in determining and monitoring the therapy process. In this paper, we apply two different methods for predicting the voice quality ratings of TE speakers by naive listeners: (a) conventional spectral and linear prediction measurements that were investigated in earlier studies, and (b) a methodology based on a perceptual auditory model that attempts to mimic the speech quality perception by a normal hearing listener. Experimental results with a database of 35 TE speakers showed that the auditory-model based approach significantly outperforms the traditional methods.