Speech Synthesis Based on Hidden Markov Models and Deep Learning.
Marvin Coto-JiménezJohn Goddard ClosePublished in: Res. Comput. Sci. (2016)
Keyphrases
- deep learning
- speech synthesis
- hidden markov models
- speech recognition
- unsupervised learning
- automatic speech recognition
- vocal tract
- machine learning
- text to speech
- conditional random fields
- gesture recognition
- weakly supervised
- mental models
- speech corpus
- noisy environments
- sequential data
- speech signal
- training set
- pattern recognition
- bayesian networks