On Synthesis for Supervised Monaural Speech Separation in Time Domain.
Jingjing ChenQirong MaoDong LiuPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- supervised learning
- speech signal
- frequency domain
- facial animation
- semi supervised
- learning algorithm
- endpoint detection
- machine learning
- speech synthesis
- noisy environments
- dialogue system
- broadcast news
- speech processing
- unsupervised learning
- neural network
- audio visual
- probabilistic model
- automatic speech recognition
- multimodal interfaces
- spoken language
- text to speech
- automatic speech recognition systems
- english text
- recognition engine
- multi stream
- speaker recognition
- speaker verification
- spoken dialogue systems
- texture synthesis
- supervised classification
- active learning
- color images
- training set
- feature space
- face recognition
- feature selection