A new statistical approach for the automatic segmentation of continuous speech signals

  title={A new statistical approach for the automatic segmentation of continuous speech signals},
  author={R{\'e}gine Andr{\'e}-Obrecht},
  journal={IEEE Trans. Acoustics, Speech, and Signal Processing},
We discuss a statistical approach for the segmentation of the continuous speech signal. The purpose is to detect acoustic events by using the proposed methods. The main idea is to model the signal by an AR statistical model and to use test statistics to sequentially detect changes in the parameters of the model. The three segmentation algorithms presented here differ in the assumption of the excitation of the model (the glottal impulses can be either taken into account or not) and in the choice… CONTINUE READING
Highly Cited
This paper has 236 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 139 extracted citations

237 Citations

Citations per Year
Semantic Scholar estimates that this publication has 237 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-9 of 9 references

Decodage acoustique phonetique de la parole continue iiiultilocuteur: Elaboration d'une b a r de connaissance.

  • N . Vigouroux
  • These de 3eme cycle." Toulouw,
  • 1984

Organisation seginentable et ternporelle du signal de parole en fonction de \a production,

  • I C . Abry
  • Rapport lnstitut de Phonetique Grenoble
  • 1984


  • CNRS.
  • 309-330.
  • 1982

Liiirclr Prrelictiori of SpeecVi

  • J . D. Markel, A. H. Gray
  • New York: Springer-Verlag
  • 1976

Inference about the change point from cumulative sum tests.

  • D. V . Hinkley
  • Bioiwrrikcr
  • 1971

On information and suficiency.

  • S. Kullback, A. Leibler
  • 1951

Similar Papers

Loading similar papers…