Explaining Deep Learning Models for Speech Enhancement.
Sunit SivasankaranEmmanuel VincentDominique FohrPublished in: Interspeech (2021)
Keyphrases
- learning models
- speech enhancement
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- machine learning
- speech signal
- linear prediction
- learning tasks
- vocal tract
- learning algorithm
- semi supervised learning
- conditional random fields
- machine learning algorithms
- loss function
- learning problems
- background noise
- classification models
- speech recognition
- multi channel
- smoothing algorithm
- additive noise
- graphical models
- active learning
- frequency domain