The Effect of Spoken Language on Speech Enhancement Using Self-Supervised Speech Representation Loss Functions.
George CloseThomas HainStefan GoetzePublished in: WASPAA (2023)
Keyphrases
- spoken language
- loss function
- speech enhancement
- dialogue system
- pairwise
- speech signal
- noisy environments
- semantic analysis
- language processing
- recognition errors
- signal to noise ratio
- noise reduction
- loss minimization
- spontaneous speech
- support vector
- wiener filter
- vocal tract
- smoothing algorithm
- background noise
- single channel
- pattern recognition
- linear prediction
- speech recognition
- high dimensional