Method and apparatus for editing speech, and method for synthesizing speech

An apparatus for editing speech, comprising:

• a generation unit configured to generate speech information from a text, the speech information including phonologic information and prosody information;
• a division unit configured to divide the speech information into a plurality of speech units, based on at least one of the phonologic information and the prosody information;
• a search unit configured to search at least two speech units from the plurality of speech units, at least one of the phonologic information and the prosody information in the at least two speech units are identical or similar;
• and
• a storing unit configured to store a speech unit waveform corresponding to one of the at least two speech units as a representative speech unit.

A method for synthesizing speech, comprising:

• generating pronunciation data including phonologic information of a text;
• retrieving a plurality of speech unit waveforms and phonologic information corresponding to the speech unit waveforms from a memory, based on the pronunciation data;
• and
• synthesizing a speech waveform of the text by concatenating the plurality of speech unit waveforms,
• wherein, in the phonologic information corresponding to the speech unit waveforms, the first and the last of each speech unit waveform correspond to an unvoiced sound or a pause sound.