Title :
AR model estimation from quantized signals
Author :
Biscainho, Luiz W P
Author_Institution :
Univ. Fed. do Rio de Janeiro: LPS-DEL/POLI, Rio de Janeiro, Brazil
Abstract :
This letter investigates the deviation of least squares AR-model estimates induced by linear quantization of the observable signal under modeling. Model correction is attained by describing the undesirable bias as a function of the number of bits used to represent the signal. Sensitivity considerations are employed to explain the behavior of the deviations on the generator filter poles. Numerical examples are included.
Keywords :
audio signal processing; autoregressive processes; estimation theory; least squares approximations; quantisation (signal); audio processing; autoregressive-model estimation; generator filter pole; least square deviation estimate; linear quantization; model correction; quantized signal; sensitivity; undesirable bias description; Binary sequences; Computational modeling; Filters; Frequency estimation; Interpolation; Least squares approximation; Maximum likelihood estimation; Quantization; Resonance; Signal processing;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2003.821683
