Zero-Shot Personalized Speech Enhancement Through Speaker-Informed Model Selection.
Aswin SivaramanMinje KimPublished in: WASPAA (2021)
Keyphrases
- model selection
- speech enhancement
- vocal tract
- noise reduction
- noisy environments
- speech signal
- signal to noise ratio
- speech recognition
- cross validation
- automatic speech recognition
- single channel
- hyperparameters
- parameter estimation
- linear prediction
- speech synthesis
- mixture model
- wiener filter
- model selection criteria
- selection criterion
- smoothing algorithm
- background noise
- machine learning
- motion segmentation
- feature selection
- adaptive filtering
- information criterion
- prior information
- language model
- image sequences
- image processing