A new Automatic Formant Tracking approach based on scalogram maxima detection using complex wavelets

Imen Jemaa 1 Kais Ouni 1 Yves Laprie 2 Slim Ouni 2 Jean-Paul Haton 2
2 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : In this paper we present a new formant tracking algorithm where the formant frequencies estimation was based on local maxima detection of a time frequency representation. This representation can be shown by a scalogram issued from a complex wavelet transform. The formant frequency candidates are validated as local maxima of scalogram which correspond to wavelet ridges. Then in the proposed algorithm, we have introduced the computation of center of gravity as tracking constraint. We tested our new algorithm by applying it on synthesized and natural voiced speech signals. The formant trajectories obtained by our algorithm were compared to those of manually-edited ones of our Arabic database as reference; those given by Fourier transform method and the LPC analysis used in Praat. The comparison of the results showed globally the adequacy of the first three formant trajectories using complex Morlet wavelet refers to the manually-edited formant tracks.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-00836854
Contributor : Yves Laprie <>
Submitted on : Friday, June 21, 2013 - 3:43:28 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Sunday, September 22, 2013 - 4:10:14 AM

File

papierCEIT13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00836854, version 1

Collections

Citation

Imen Jemaa, Kais Ouni, Yves Laprie, Slim Ouni, Jean-Paul Haton. A new Automatic Formant Tracking approach based on scalogram maxima detection using complex wavelets. CEIT - International Conference on Control, Engineering & Information Technology - 2013, Jun 2013, Sousse, Tunisia. ⟨hal-00836854⟩

Share

Metrics

Record views

754

Files downloads

519