A Deep Learning Speech Enhancement Architecture Optimised for Speech Recognition and Hearing Aids.
Soha A. NossierJulie A. WallMansour MoniriCornelius GlackinNigel CanningsPublished in: ICTAI (2023)
Keyphrases
- speech recognition
- hearing aids
- deep learning
- speech signal
- speech enhancement
- spectral subtraction
- noisy environments
- noisy speech
- automatic speech recognition
- hidden markov models
- unsupervised learning
- vocal tract
- speaker identification
- linear prediction
- language model
- background noise
- noise reduction
- pattern recognition
- speech synthesis
- single channel
- signal to noise ratio
- additive noise
- machine learning
- face recognition
- neural network
- feature extraction
- non stationary
- bit rate
- high dimensional