2011
DOI: 10.1109/tsp.2011.2105482
|View full text |Cite
|
Sign up to set email alerts
|

Model Selection for Sinusoids in Noise: Statistical Analysis and a New Penalty Term

Abstract: Abstract-Detection of the number of sinusoids embedded in noise is a fundamental problem in statistical signal processing. Most parametric methods minimize the sum of a data fit (likelihood) term and a complexity penalty term. The latter is often derived via information theoretic criteria, such as minimum description length (MDL), or via Bayesian approaches including Bayesian information criterion (BIC) or maximum a-posteriori (MAP). While the resulting estimators are asymptotically consistent, empirically the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
67
0

Year Published

2011
2011
2017
2017

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 43 publications
(69 citation statements)
references
References 40 publications
2
67
0
Order By: Relevance
“…The 3k unidentified parameters are estimated by the grid search, i.e., all possible values of frequency and phase (amplitude can be estimated using the assumed frequency and phase by using this relation;â j = t x(t) sin(ω j t+φ) t (x(t) sin(ω j t+φ)) 2 [140] are tested and the one maximizing the likelihood function (66) is selected as the best estimate.…”
Section: Preliminariesmentioning
confidence: 99%
“…The 3k unidentified parameters are estimated by the grid search, i.e., all possible values of frequency and phase (amplitude can be estimated using the assumed frequency and phase by using this relation;â j = t x(t) sin(ω j t+φ) t (x(t) sin(ω j t+φ)) 2 [140] are tested and the one maximizing the likelihood function (66) is selected as the best estimate.…”
Section: Preliminariesmentioning
confidence: 99%
“…The implication of such a conclusion is that if one pursues an approach based on the generalized likelihood ratio test (GLRT) between ML estimates of models of different orders (see [20]) they may find a penalty term that does not exactly satisfy the EDC consistency requirements, but indeed results in consistent model selection with interestingly good performance for finite-sample cases. Based on this, [20] provides a new penalty term based on extreme value theory results on the excursion probability of Gaussian random fields. Such random fields are associated with the GLRT for the sinusoid model selection problem when the observations are scalar.…”
Section: Introductionmentioning
confidence: 99%
“…Such random fields are associated with the GLRT for the sinusoid model selection problem when the observations are scalar. More precisely, [20] shows that for such assumptions, the distribution of the GLRT is related to the distribution of maxima of a two-dimensional Gaussian random field since two parameters, frequency and phase, are needed to be estimated for each successive model order. In the case of complex-valued vector observations that we deal with in this paper, we show that the GLRT distribution is related to the distribution of maxima of a one dimensional (only frequency dimension) chi-square random field.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The tonality detection itself is a common problem in many different technical aspects. From radio or echolocation (radar or sonar) [7] through detection of birds in noisy environment [8] to perceptual audio coding [9]. This short list of examples shows how diverse a domain of tones detection is.…”
Section: Introductionmentioning
confidence: 99%