Enhancing Intelligibility of Dysarthric Speech Using Gated Convolutional-Based Voice Conversion System.
Chen-Yu ChenWei-Zhong ZhengSyu-Siang WangYu TsaoPei-Chun LiYing-Hui LaiPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- text to speech
- speech synthesis
- voice activity detection
- speech recognition errors
- emotion recognition
- speech sounds
- speech quality
- speech signal
- fundamental frequency
- prosodic features
- hidden markov models
- audio visual
- sparse coding
- synthesized speech
- noisy environments
- recognition engine
- speech processing
- endpoint detection
- vocal tract
- spoken dialogue systems
- speaker identification
- natural images
- english text
- multimodal interaction
- language model
- neural network
- machine learning
- automatic speech recognition systems
- data conversion
- mel frequency cepstral coefficients
- word processing
- speaker recognition
- spoken language
- deep learning
- language acquisition
- facial expressions
- pattern recognition
- face recognition