Improving Reverberant Speech Separation with Binaural Cues Using Temporal Context and Convolutional Neural Networks.
Alfredo ZerminiQiuqiang KongYong XuMark D. PlumbleyWenwu WangPublished in: LVA/ICA (2018)
Keyphrases
- temporal context
- audio visual
- sound source
- convolutional neural networks
- speech signal
- visual context
- speech recognition
- spatial context
- multi modal
- temporal information
- visual information
- spatio temporal
- convolutional network
- language model
- visual data
- high level
- multimedia
- hidden markov models
- spatial and temporal
- mid level
- image database
- image data
- image segmentation