Robust Segmentation of Speech Signal Using MFCC and Acoustic Parameters.
Zhandos YessenbayevPublished in: Asia International Conference on Modelling and Simulation (2012)
Keyphrases
- speech signal
- robust segmentation
- acoustic features
- speech recognition
- mel frequency cepstral coefficients
- speaker identification
- automatic speech recognition
- noisy speech
- spectral analysis
- speech sounds
- sound source
- background noise
- non stationary
- hidden markov models
- noisy environments
- vocal tract
- speaker recognition
- linear prediction
- speech enhancement
- shape prior
- cepstral coefficients
- parameter estimation
- iris recognition
- speech quality
- expectation maximization
- automatic speech recognition systems
- music information retrieval
- fundamental frequency
- speaker verification
- gaussian mixture model
- visual features
- level set
- language model