Listen, Think and Listen Again: Capturing Top-down Auditory Attention for Speaker-independent Speech Separation.
Jing ShiJiaming XuGuangcan LiuBo XuPublished in: IJCAI (2018)
Keyphrases
- speech recognition
- speaker independent
- speaker dependent
- hidden markov models
- speaker identification
- speech recognizer
- digit recognition
- speech recognition systems
- speech signal
- automatic speech recognition
- speech synthesis
- pattern recognition
- high level
- audio visual
- acoustic models
- language model
- speaker adaptation
- spoken language
- visual attention
- visual information
- low level