Speech Separation Based on DPTNet with Sparse Attention.
Beom Jun WooHyung Yong KimJeunghun KimNam Soo KimPublished in: IC-NIDC (2021)
Keyphrases
- high dimensional
- speech recognition
- autistic children
- audio visual
- focus of attention
- sparse representation
- speech signal
- language acquisition
- sparse data
- speech synthesis
- text to speech
- broadcast news
- spoken language
- machine learning
- dialogue system
- compressed sensing
- real time
- linear prediction
- automatic speech recognition
- multi modal
- bayesian networks
- image sequences
- recognition engine