The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions.
George CloseThomas HainStefan GoetzePublished in: CoRR (2023)
Keyphrases
- spoken language
- loss function
- speech enhancement
- dialogue system
- noisy environments
- speech signal
- pairwise
- spontaneous speech
- recognition errors
- noise reduction
- single channel
- semantic analysis
- vocal tract
- language processing
- loss minimization
- signal to noise ratio
- support vector
- convex loss functions
- machine learning
- wiener filter
- non stationary
- natural language
- pattern recognition
- similarity measure
- linear prediction
- semantic knowledge
- language model
- noisy speech
- image processing