# Lower and upper bounds for approximation of the Kullback-Leibler divergence between Gaussian Mixture Models

@article{Durrieu2012LowerAU, title={Lower and upper bounds for approximation of the Kullback-Leibler divergence between Gaussian Mixture Models}, author={Jean-Louis Durrieu and J. Thiran and Finnian Kelly}, journal={2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2012}, pages={4833-4836} }

Many speech technology systems rely on Gaussian Mixture Models (GMMs). The need for a comparison between two GMMs arises in applications such as speaker verification, model selection or parameter estimation. For this purpose, the Kullback-Leibler (KL) divergence is often used. However, since there is no closed form expression to compute it, it can only be approximated. We propose lower and upper bounds for the KL divergence, which lead to a new approximation and interesting insights into… Expand

#### 46 Citations

Upper and lower bounds for approximation of the Kullback-Leibler divergence between Hidden Markov models

- Mathematics, Computer Science
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2013

Guaranteed Bounds on the Kullback–Leibler Divergence of Univariate Mixtures

- Mathematics, Computer Science
- IEEE Signal Processing Letters
- 2016

40- PDF

Close Approximation of Kullback–Leibler Divergence for Sparse Source Retrieval

- Mathematics, Computer Science
- IEEE Signal Processing Letters
- 2019

1

Guaranteed Bounds on Information-Theoretic Measures of Univariate Mixtures Using Piecewise Log-Sum-Exp Inequalities

- Mathematics, Computer Science
- Entropy
- 2016

36- PDF

On the Minimax Risk of Dictionary Learning

- Mathematics, Computer Science
- IEEE Transactions on Information Theory
- 2016

27- PDF

GUARANTEED DETERMINISTIC BOUNDS ON THE TOTAL VARIATION DISTANCE BETWEEN UNIVARIATE MIXTURES

- Computer Science, Mathematics
- 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)
- 2018

2- PDF

On the Properties of Kullback-Leibler Divergence Between Gaussians

- Computer Science, Mathematics
- ArXiv
- 2021

- PDF

Enhanced Multiple Model GPB2 Filtering Using Variational Inference

- Computer Science, Mathematics
- 2019 22th International Conference on Information Fusion (FUSION)
- 2019

#### References

SHOWING 1-10 OF 13 REFERENCES

Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models

- Mathematics, Computer Science
- 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
- 2007

717 Highly Influential- PDF

Accelerated Monte Carlo for Kullback-Leibler divergence between Gaussian mixture models

- Mathematics, Computer Science
- 2008 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2008

15

Simple and efficient speaker comparison using approximate KL divergence

- Computer Science
- INTERSPEECH
- 2010

24- PDF

A new SVM approach to speaker identification and verification using probabilistic distance kernels

- Computer Science
- INTERSPEECH
- 2003

50- PDF

Speaker Verification Using Adapted Gaussian Mixture Models

- Computer Science
- Digit. Signal Process.
- 2000

4,445- PDF

Variational Bayes for generalized autoregressive models

- Mathematics, Computer Science
- IEEE Trans. Signal Process.
- 2002

152- PDF

Support vector machines using GMM supervectors for speaker verification

- Computer Science
- IEEE Signal Processing Letters
- 2006

1,018- PDF

Speaker diarization using bottom-up clustering based on a parameter-derived distance between adapted GMMs

- Computer Science
- INTERSPEECH
- 2004

77- PDF