Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis.
Keiichi TokudaHeiga ZenPublished in: ICASSP (2015)
Keyphrases
- speech synthesis
- speech recognition
- neural network
- text to speech
- vocal tract
- prosodic features
- statistical modeling
- speech corpus
- pattern recognition
- artificial neural networks
- hidden markov models
- statistical models
- information theoretic
- data driven
- fuzzy logic
- automatic speech recognition
- self organizing maps
- speech signal
- statistical analysis
- neural nets
- multi layer
- back propagation
- statistical inference
- speaker identification
- language model
- recognition engine
- genetic algorithm