Project description
|
◦ Speech recorded for prosody synthesis
◦ 1 professional male announcer
◦ Soundproof room
◦ Microphone: Rode NT-2 mic.
◦ EGG signal: Laryngograph 6103
◦ Sampling and data format
- 16,000 Hz, 16 bit Windows wave format
◦ Text corpus for selection of prompts
- KAIST Tagged Corpus of 1,000,000 words
◦ 4,392 sentences selected according to triphone frequency |