Improved modelling of speech dynamics using non-linear formant trajectories for HMM-based speech synthesis.
Hongwei HuMartin J. RussellPublished in: INTERSPEECH (2010)
Keyphrases
- speech synthesis
- speech recognition
- vocal tract
- hidden markov models
- speech signal
- text to speech
- speech corpus
- prosodic features
- automatic speech recognition
- speech recognizer
- pattern recognition
- dynamic model
- dynamical systems
- speaker identification
- language model
- speech recognition systems
- speaker independent
- neural network
- moving objects
- noisy environments
- trajectory data
- handwriting recognition
- phase space
- human computer interaction
- kinematic model