Self-Supervised Speech Enhancement for Arabic Speech Recognition in Real-World Environments.
Bilal DendaniHalima BahiToufik SariPublished in: Traitement du Signal (2021)
Keyphrases
- speech recognition
- speech enhancement
- noisy environments
- speech signal
- isolated word
- noisy speech
- vocal tract
- speech synthesis
- automatic speech recognition
- hidden markov models
- language model
- background noise
- pattern recognition
- speaker identification
- noise reduction
- linear prediction
- signal to noise ratio
- additive noise
- single channel
- spectral analysis
- word recognition
- information retrieval
- multi channel
- speaker diarization
- spectral subtraction
- multiresolution