Deep Feed-forward Sequential Memory Networks for Speech Synthesis.
Mengxiao BiHeng LuShiliang ZhangMing LeiZhijie YanPublished in: CoRR (2018)
Keyphrases
- feed forward
- speech synthesis
- speech recognition
- recurrent networks
- back propagation
- neural nets
- text to speech
- artificial neural networks
- recurrent neural networks
- neural network
- biologically plausible
- spiking neural networks
- spiking neurons
- vocal tract
- social networks
- visual cortex
- memory requirements
- hidden layer
- prosodic features
- neural architecture
- error back propagation
- activation function
- artificial neural
- computer vision
- feed forward neural networks
- main memory
- complex networks
- multi layer
- language model
- pattern recognition
- support vector