NOMAD: Unsupervised Learning of Perceptual Embeddings for Speech Enhancement and Non-matching Reference Audio Quality Assessment.
Alessandro RaganoJan SkoglundAndrew HinesPublished in: CoRR (2023)
Keyphrases
- quality assessment
- unsupervised learning
- reduced reference
- human visual system
- speech enhancement
- image quality assessment
- image quality
- visual information
- video quality
- noisy environments
- noise reduction
- dimensionality reduction
- signal to noise ratio
- speech signal
- quality metrics
- data quality
- single channel
- perceptual image quality
- visual quality
- human perception
- audio visual
- signal processing
- machine learning
- expectation maximization
- linear prediction
- data mining
- coding scheme
- pattern recognition
- multiscale
- high quality
- feature extraction