Explicit duration modelling in HMM-based speech synthesis using continuous hidden Markov Model.
Udochukwu OgburekeJoão P. CabralJulie Carson-BerndsenPublished in: ISSPA (2012)
Keyphrases
- hidden markov models
- speech synthesis
- speech recognition
- hidden semi markov models
- variable duration
- vocal tract
- text to speech
- automatic speech recognition
- conditional random fields
- speech signal
- sequential data
- dynamic probabilistic networks
- speech corpus
- hidden states
- discriminative training
- markov models
- handwritten word recognition
- speaker identification
- hidden state
- phoneme recognition
- viterbi algorithm
- neural network
- abnormality detection
- probabilistic model
- noisy environments