Generating fundamental frequency contours for speech synthesis in yorùbá.
Daniel R. van NiekerkEtienne BarnardPublished in: INTERSPEECH (2013)
Keyphrases
- speech synthesis
- fundamental frequency
- speech recognition
- speech signal
- text to speech
- vocal tract
- prosodic features
- active contours
- automatic speech recognition
- hidden markov models
- generation process
- endpoints
- contour matching
- neural network
- wavelet coefficients
- information retrieval systems
- image contours
- pattern recognition
- multiscale
- three dimensional
- information retrieval
- machine learning