Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra.
Toru NakashikaShinji TakakiJunichi YamagishiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2019)
Keyphrases
- complex valued
- speaker dependent
- real valued
- speech recognition
- recurrent neural networks
- speaker identification
- restricted boltzmann machine
- deep learning
- speaker independent
- speech recognizer
- neural network
- activation function
- hidden layer
- language model
- semi supervised
- broadcast news
- hidden markov models
- machine learning