English speech sound improvement system based on deep learning from signal processing to semantic recognition.
Yucheng YangYibo YuePublished in: Int. J. Speech Technol. (2020)
Keyphrases
- deep learning
- signal processing
- automatic speech recognition systems
- unsupervised learning
- natural language
- text to speech
- pattern recognition
- unsupervised feature learning
- english text
- speech recognition
- broadcast news
- image processing
- object recognition
- machine learning
- speech signal
- weakly supervised
- feature extraction
- semantic similarity
- semantic information
- mental models
- partial occlusion
- question answering
- dimensionality reduction
- feature selection