Characteristics of roughness in esophageal speech

Abstract

Esophageal voice, produced by the vibration of the superior sphincter of the esophagus by persons who have been laryngectomized, is almost invariably associated with voice source roughness. Using inverse filtering of speech recorded to minimize phase distortion, the source characteristics of six esophageal speakers with different levels of proficiency were examined. With our three less proficient speakers, the roughness is clearly evident in the volume velocity waveform. Highly proficient esophageal speakers, however, although they have a voice quality which is perceived as rough, nevertheless produce a volume velocity waveform surprisingly similar to that of laryngeal speakers. The characteristics that produce this perceived roughness, other than jitter and shimmer, are difficult to detect in the volume velocity waveform. They are noise components of low amplitude and relatively high frequency, which are attenuated in the (integrated) volume velocity. They are best observed in the differentiated volume velocity waveform or in spectral measures. Our results suggest that the volume velocity waveform may not be a very effective measure for evaluating the speech of highly proficient esophageal speakers.