Automatic pitch marking for speech transformations via TD-PSOLA.
Yves LaprieVincent ColottePublished in: EUSIPCO (1998)
Keyphrases
- speech recognition
- fully automatic
- fundamental frequency
- spoken language
- temporal difference
- decision making
- recognition engine
- text to speech
- multi modal
- formant frequencies
- data sets
- multi stream
- acoustic features
- automatic speech recognition
- speech signal
- audio visual
- semi automatic
- natural language processing
- feature vectors
- pattern recognition
- reinforcement learning
- case study
- information retrieval
- neural network