Self-Adjustable Speech Enhancement and Recognition System.
Tomoko KawaseManabu OkamotoTakaaki FukutomiYamato TakahashiRyota MasudaTakayuki OotakePublished in: ICCE (2019)
Keyphrases
- speech enhancement
- noisy speech
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- speech signal
- linear prediction
- background noise
- vocal tract
- speech recognition
- wiener filter
- additive noise
- feature extraction
- smoothing algorithm
- hidden markov models
- edge detection
- edge preserving
- multi channel
- frequency domain
- multiresolution
- automatic speech recognition
- information retrieval
- independent component analysis
- probabilistic model
- computational complexity
- computer vision