Article

The purpose of this study is to develop a tool to assist speech therapy and
rehabilitation, which focused on automatic scoring based on the comparison of the
patient's speech with another normal speech on several aspects including pitch,
vowel, voiced-unvoiced segments, strident fricative and sound intensity. The
pitch estimation employed the use of cepstrum-based algorithm for its robustness;
the vowel classification used multilayer perceptron (MLP)
to classify vowel from
pitch and formants; and the strident fricative detection was based on the major
peak spectral intensity, location and the pitch existence in the segment. In
order to evaluate the performance of the system, this study analyzed eight
patient's speech recordings (four males, four females; 4-58-years-old), which had
been recorded in previous study in cooperation with Taipei Veterans General
Hospital and Taoyuan General Hospital. The experiment result on pitch algorithm
showed that the cepstrum method had 5.3% of gross pitch error from a total of
2086 frames. On the vowel classification algorithm, MLP method provided 93%
accuracy (men), 87% (women) and 84% (children). In total, the overall results
showed that 156 tool's grading results (81%) were consistent compared to 192
audio and visual observations done by four experienced respondents. Implication
for Rehabilitation Difficulties in communication may limit the ability of a
person to transfer and exchange information. The fact that speech is one of the
primary means of communication has encouraged the needs of speech diagnosis and
rehabilitation. The advances of technology in computer-assisted speech therapy
(CAST) improve the quality, time efficiency of the diagnosis and treatment of the
disorders. The present study attempted to develop tool to assist speech therapy
and rehabilitation, which provided simple interface to let the assessment be done
even by the patient himself without the need of particular knowledge of speech
processing while at the same time, also provided further deep analysis of the
speech, which can be useful for the speech therapist.

Langue : ANGLAIS