DMANET: Deep Learning-Based Differential Microphone Arrays for Multi-Channel Speech Separation.
Xiaokang YangJianguo WeiPublished in: ICASSP (2022)
Keyphrases
- deep learning
- multi channel
- automatic speech recognition
- sound source
- speech signal
- single channel
- speech recognition
- speaker diarization
- unsupervised learning
- machine learning
- audio visual
- unsupervised feature learning
- mental models
- hidden markov models
- visual information
- deep architectures
- multiscale
- model selection
- signal processing
- medical images
- viewpoint
- pattern recognition