On a hybrid time domain-LPC technique for prosody superimposing used for speech synthesis.
Attila FerenczIstván NagyTunde-Csilla KovácsTeodora RatiuMaria FerenczPublished in: EUROSPEECH (1999)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- vocal tract
- hidden markov models
- speech signal
- speech corpus
- frequency domain
- automatic speech recognition
- language model
- pattern recognition
- feature selection
- genetic algorithm
- non stationary
- wavelet transform
- hybrid learning
- speaker identification
- case study
- knowledge base