Deep Learning Networks for Vowel Speech Imagery.
José Manuel Macías-MacíasJuan Alberto Ramirez-QuintanaGraciela Ramírez AlonsoMario Ignacio Chacon MurguiaPublished in: CCE (2020)
Keyphrases
- deep learning
- speech signal
- speech synthesis
- formant frequencies
- unsupervised learning
- vocal tract
- fundamental frequency
- unsupervised feature learning
- speech recognition
- machine learning
- mental models
- image processing
- prosodic features
- text to speech
- deep architectures
- weakly supervised
- automatic speech recognition
- semi supervised
- object recognition
- computer vision
- speech recognition systems
- high resolution