Performance enhancement of text-independent speaker recognition in noisy and reverberation conditions using Radon transform with deep learning.
Samia Abd El-MoneimEman Abd El-MordyMohamed Abd-Elsalam NassarMoawad I. DessoukyNabil A. IsmailAdel S. El-FishawySami Abdelmeneem EldolilIbrahim M. El-DokanyFathi E. Abd El-SamiePublished in: Int. J. Speech Technol. (2022)
Keyphrases
- radon transform
- deep learning
- unsupervised learning
- image reconstruction
- fourier transform
- noisy images
- recognition rate
- feature detection
- object recognition
- straight line
- pattern recognition
- signal processing
- hough transform
- machine learning
- frequency domain
- image processing
- feature extraction
- pattern analysis
- weakly supervised
- similarity measure
- three dimensional
- mental models