Lotfi Messikh  , Mouldi Bedda  , 
    Performance Comparison of Two Joint Three States  Segmentation and AR Modelling Algorithms,
    Research Journal of Applied Sciences,
    Volume 2,Issue 6,
    2007,
    Pages 704-707,
    ISSN 1815-932x,
    rjasci.2007.704.707,
    (https://makhillpublications.co/view-article.php?doi=rjasci.2007.704.707)
    Abstract: Two procedures designed for the joint segmentation and AR modelling of quasi-stationary signal-the Rate/Distortion Algorithm (RDA) and the Maximum Likelihood Algorithm (MLA) - are compared regarding their performance. Both algorithms share a same parameters estimation process and differ only in the form of the criterion to be optimised. The comparison is achieved with 2 simple indexes on the phonemes Otago data corpus assuming a 3 state model of the same order for each phoneme. As a general result, it is shown that the MLA is less sensitive to AR order choice and perform the least model residual correlations.
    Keywords: Linear prediction;non-stationary;signal segmentation;rate-distortion;maximum likelihood estimation