Noise-robust cortical tracking of attended speech in real-world acoustic scenes.
Søren Asp FuglsangTorsten DauJens HjortkjærPublished in: NeuroImage (2017)
Keyphrases
- real world
- noisy environments
- robust tracking
- object tracking algorithm
- dynamic background
- image noise
- speech recognition
- partial occlusion
- cluttered environments
- real time
- speech enhancement
- speech recognition systems
- noisy speech
- speaker verification
- tracking framework
- prosodic features
- data sets
- speech signal
- particle filter
- noise level
- motion segmentation
- cluttered background
- geometric distortions
- noise reduction
- background noise
- visual tracking
- denoising
- object tracking
- kalman filter
- speech sounds
- salt pepper
- audio stream
- emotional speech
- video data
- missing data
- mean shift
- estimation error
- text to speech
- dynamic scenes
- multiple objects