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