Foreground Speech Segmentation and Enhancement Using Glottal Closure Instants and Mel Cepstral Coefficients.
K. T. DeepakS. R. Mahadeva PrasannaPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- cepstral coefficients
- speech signal
- speech recognition
- linear predictive coding
- automatic speech recognition
- linear predictive
- linear prediction
- noisy environments
- speaker identification
- image segmentation
- hidden markov models
- non stationary
- foreground and background
- feature set
- mel frequency cepstral coefficients
- spectral analysis
- acoustic features
- object segmentation
- pattern recognition
- language model
- audio signal
- edge detection
- sound source
- noisy images
- multiscale
- multi modal
- image processing