Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation.
William RavenscroftStefan GoetzeThomas HainPublished in: CoRR (2022)
Keyphrases
- machine learning
- speech signal
- noisy environments
- deep learning
- speech recognition
- pattern recognition
- spatial and temporal
- automatic speech recognition
- network analysis
- temporal constraints
- spatio temporal
- sound source
- social networks
- temporal consistency
- complex networks
- network structure
- temporal reasoning
- noisy data
- temporal patterns
- temporal information
- network design
- heterogeneous networks
- temporal dimension
- unsupervised learning
- space time
- non stationary
- spoken language
- network size
- speaker identification
- text to speech