Guided Variational Autoencoder for Speech Enhancement with a Supervised Classifier.
Guillaume CarbajalJulius RichterTimo GerkmannPublished in: ICASSP (2021)
Keyphrases
- speech enhancement
- supervised classifiers
- supervised classification
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- speech signal
- linear prediction
- data sets
- training set
- vocal tract
- semi supervised learning
- image segmentation
- smoothing algorithm
- sentiment analysis
- wiener filter
- labeled data
- optical flow
- background noise
- image coding
- speech recognition
- unsupervised learning
- edge detection
- multi channel
- additive noise
- prior knowledge
- high dimensional
- bayesian networks
- feature selection
- machine learning