a voice segment acquisition section that acquires a voice segment including one or more phonemes;

a boundary designation section that designates a boundary intermediate between start and end positions of a vowel phoneme included in the voice segment acquired by the voice segment acquisition section,

wherein when the acquired voice segment where a region including an end point is a vowel phoneme, the boundary designation section designates, as the boundary, a time point earlier than a stationary point, which is a boundary point between a region where a waveform amplitude of the voice segment is substantially constant and a region where the waveform amplitude of the voice segment varies, and

wherein when the acquired voice segment where a region including a start point is a vowel phoneme, the boundary designation section designates, as the boundary, a time point later than the stationary point; and

a voice synthesis section that synthesizes a voice based on a region of the vowel phoneme that precedes the designated boundary of the vowel phoneme, or a region of the vowel phoneme that succeeds the designated boundary of the vowel phoneme,

wherein the start point and the end point of the vowel phoneme and the designated boundary of the vowel phoneme are time points on a time axis of the acquired voice segment,

wherein when the acquired voice segment where the region including the end point is a vowel phoneme, the voice synthesis section synthesizes the voice based on the region of the voice segment preceding the boundary designated by the boundary designation section, and

wherein when the acquires voice segment where the region including the start point is a vowel phoneme, the voice synthesis section synthesizes the voice based on the region of the voice segment succeeding the boundary designated by the boundary designation section.