The use of maximum a posteriori parameters in linear prediction of speech.
Gaafar M. K. SalehMahesan NiranjanWilliam J. FitzgeraldPublished in: EUROSPEECH (1995)
Keyphrases
- linear prediction
- maximum a posteriori
- maximum likelihood
- expectation maximization
- speech signal
- map estimation
- markov random field
- image coding
- generalized gaussian
- autoregressive
- prediction error
- image reconstruction
- em algorithm
- lossless compression
- parameter estimation
- prior model
- model parameters are estimated
- vocal tract
- label field
- energy function
- likelihood function
- subband
- non stationary
- spectral analysis
- image segmentation
- speech recognition
- gaussian mixture model
- filter bank
- image quality
- least squares
- pattern recognition
- image processing