Improvement of esophageal speech by adaptive line enhancement with bias model
Proceedings of the 2nd International Convention on Rehabilitation Engineering & Assistive Technology
| Hi-index | 0.00 |
Esophageal speeches of 7 laryngectomy persons were evaluated post modified by the Speech enhancer program®. Five speech-language pathologists assessed their speech accuracy and intelligibility of the words and continuing speech. Each speech sample was compared pre and post modified. It was found that originally all esophageal speakers had various articulation disorders. The error patterns were substitution, addition, omission and distortion. These speech defects seemed to relate to structure and source of speech changed after laryngectomy. After converted by the Speech enhancer program®, accuracy of the word level increased in 8.14±7.21 phonemes. In contrast, accuracy decreased in 9.14±9.24 phonemes. Furthermore, there were 18.87±14.5 phonemes and 32±5.66 phonemes that remained accurate and inaccurate, respectively. For speech intelligibility, there was no difference perceived between the original speech and the converted speech with the rating scale of 2 and 4 for intelligibility of words and continuing speech, respectively. In addition, the converted speech was perceived subjectively that it was subtlety clearer than and more intelligible than the original speech. In addition, pitches of the converted speech were perceived to be higher or lower in comparison to the original ones. Moreover, converted speech was perceived as soft voice. Furthermore, perceived rough, strain, unpleasant and unnatural speech characteristic in the converted speech were noted. This study implied that the Speech enhancer program® might have some benefit for esophageal speakers as it could enhance changes. Evidently transforming the program was indicated for future implementation the program. Further study is recommended to conduct in a larger population group to reveal the speech patterns and related factors.