Improvement of automatic speech recognition systems via nonlinear dynamical features evaluated from the recurrence plot of speech signals.
Shabnam Gholamdokht FiroozFarshad AlmasganjYasser ShekoftehPublished in: Comput. Electr. Eng. (2017)
Keyphrases
- automatic speech recognition systems
- speech signal
- speech recognition
- nonlinear dynamical
- mel frequency cepstral coefficients
- hidden markov models
- non stationary
- noisy environments
- automatic speech recognition
- background noise
- spectral analysis
- additive noise
- multiscale
- speaker identification
- feature vectors
- feature space
- pattern recognition