Robust and high-resolution voiced/unvoiced classification in noisy speech using a signal smoothness criterion.
A. Sreenivasa MurthyS. Chandra SekharThippur V. SreenivasPublished in: INTERSPEECH (2007)
Keyphrases
- speech signal
- high resolution
- noisy speech
- noisy environments
- high frequency
- feature selection
- feature extraction
- pattern recognition
- support vector
- feature space
- signal processing
- speech recognition
- non stationary
- classification accuracy
- super resolution
- image processing
- frequency domain
- neural network
- additive noise
- mel frequency cepstral coefficients
- machine learning