| 摘要 |
<p>A system for synthesizing a speech signal from strings of words (1005) includes a memory (1010) in which predetermined syntax tags are stored in association with entered words and phonetic transcriptions are stored in association with the syntax tags. A parser (1040) accesses the memory and groups the syntax tags into phrases according to a first set of predetermined grammatical rules relating the syntax tags to one another. The parser also verifies the conformance of sequences of the phrases to a second set of rules relating phrases to one another. The system retrieves the phonetic transcription associated with the syntax tags (1080) and adds markers for rhythm and stress to the strings, which are then converted into data arrays (1110) having prosody information on a diphone-by-diphone basis. Diphone waveforms are retrieved from memory (1130) and adjusted based on the prosody information in the arrays (1120). The adjusted diphone waveforms are then concatenated to form the speech signal.</p> |
