An improved wavelet-based speech enhancement by using speech signal features.
Saeed AyatM. T. Manzuri-ShalmaniRoohollah DianatPublished in: Comput. Electr. Eng. (2006)
Keyphrases
- speech signal
- speech enhancement
- noisy environments
- noise reduction
- speech recognition
- signal to noise ratio
- vocal tract
- mel frequency cepstral coefficients
- automatic speech recognition
- linear prediction
- non stationary
- background noise
- single channel
- hidden markov models
- speaker identification
- multiresolution
- speaker recognition
- additive noise
- feature vectors
- noisy speech
- spectral analysis
- low contrast
- feature space
- feature extraction
- sound source
- feature set
- wavelet transform
- feature selection