Diphone synthesis using an overlap-add technique for speech waveforms concatenation.
Francis CharpentierM. G. StellaPublished in: ICASSP (1986)
Keyphrases
- speech recognition
- speech signal
- text to speech
- speech synthesis
- spoken language
- program synthesis
- audio visual
- texture synthesis
- facial animation
- speaker verification
- language acquisition
- recognition engine
- regular expressions
- endpoint detection
- social networks
- automatic speech recognition systems
- neural network
- speaker recognition
- emotion recognition
- automatic speech recognition
- information systems
- speaker identification
- multimodal interfaces
- human communication
- broadcast news
- audio stream
- hidden markov models