Objective: This research was conducted to evaluate the method of sasangin classification by voice analysis, The 2 pilot tests were thus designed to solve the following problems: ’’What are the conditions at classification for sasangin by the voice analysis?’’ and ’’What are the important variances of /a/ parameter?’’.
Methods: 122 volunteers Were examined to make a diagnosis of sasangin by QSCC II and they were disease-free and healthy, First, they said /a/ three times for 2 seconds in their usual voice, Second, they said /a/ for 2 seconds by the different ways of high tone, mid tone, and low tone. The sounds were collected by a recording program (cooledit 2000) through a Sony microphone (ecm-26l). We analyzed the voices by maltlab, the simulation tool.
Results: There were no differences and were correlations when one said /a/ three times for 2 seconds in the usual voice. There were some things to correlate when one said /a/ three times for 2 seconds by the different ways of high speech, usual speech, and low speech. Others were nothing to correlate. We evaluated the value of sasangin classification method by only /a/ voice analysis. The hit ratio was average $66.3\%\;:\;soyangin\;67.9\%,\;taeumin\;68.0\%,\;soeumin\;63.9\%$.
Conclusion: We must set up the conditions to use the method of sasangin classification by voice analysis. The value of sasangin classification method by only fa! voice analysis was a hit ratio of $66.3\%$.
|