A time-scaling approach to detect the closely spaced segments of noisy speech signals.
Moe PwintFarook SattarPublished in: ICECS (2003)
Keyphrases
- speech signal
- closely spaced
- noisy environments
- speech recognition
- automatic speech recognition
- speech enhancement
- automatic speech recognition systems
- formant frequencies
- background noise
- vocal tract
- spectral analysis
- non stationary
- linear prediction
- contour lines
- sound signals
- blind source separation
- hidden markov models
- additive noise
- image segmentation
- noisy images
- high frequency
- computer vision