| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a pronunciation determining method of imparting voiceless sound symbol, a device, a program, and a recording medium. <P>SOLUTION: Disclosed is the pronunciation determining method of: (A) reading in as input information a reading with an accent nucleus which needs to be decided whether or not a voiceless sound symbol is imparted, one or more readings right before the reading, one or more readings right after the reading, and information indicating whether or not the one or more readings right before the reading are given voiceless sound symbols, respectively; (C) reading out of a pronunciation determining rule storage part 101 a rule for deciding whether or not a voiceless sound symbol needs to be imparted to the reading with the accent nucleus from the reading, the one or more reading right before the reading, the one or more readings right after the reading, and the information indicating whether or not the one or more readings right before the reading are given the voiceless sound symbols respectively; and (D) deciding whether or not the voiceless sound symbol is imparted to the reading by using discrimination algorithm. <P>COPYRIGHT: (C)2006,JPO&NCIPI |
