Articulatory-to-speech Conversion Using Bi-directional Long Short-term Memory.
Fumiaki TaguchiTokihiko KaburagiPublished in: INTERSPEECH (2018)
Keyphrases
- bi directional
- speech recognition
- vocal tract
- recurrent neural networks
- long short term memory
- speech signal
- speech synthesis
- multi stream
- formant frequencies
- text to speech
- pattern recognition
- associative memory
- hidden markov models
- image acquisition
- automatic speech recognition
- language model
- acoustic features
- linear prediction
- audio visual
- speaker identification
- broadcast news
- english chinese
- learning algorithm
- emotion recognition
- fuzzy logic
- feed forward