Application of the EMD decomposition to discriminate nasalized vs. vowels phones in French - CentraleSupélec Access content directly
Conference Papers Year : 2010

Application of the EMD decomposition to discriminate nasalized vs. vowels phones in French

Abstract

This work deals with the application of the Empirical Mode Decomposition (EMD) with the goal of showing its capabilities and limitations when applied to nasalized vs. oral vowels phones classification. The method used in this study consists in three classical stages: signal preprocessing, feature extraction and decision. Firstly, the speech signal is decomposed using the EMD method so as to extract the three first Intrinsic Mode Functions (IMF). Then, Mel-Frequency Cepstral Coefficients (MFCC) are extracted from these IMFs or a (maybe partial) sum of them. Finally, an Artificial Neural Network (ANN) is used to distinguish nasal vowels from oral vowels in French (French database Bref80). Besides the fact that this study resulted in a significant improvement in the level of discrimination, when we use our method compared to the standard application of MFCC to the original signal. It has also allowed us to know which IMFs allows to better characterize the nasal vowels from the oral vowels.
No file

Dates and versions

hal-00459657 , version 1 (24-02-2010)

Identifiers

  • HAL Id : hal-00459657 , version 1

Cite

Mohamed Reda Saïdi, Olivier Pietquin, Régine André-Obrecht. Application of the EMD decomposition to discriminate nasalized vs. vowels phones in French. SPPRA 2010, Feb 2010, Innsbruck, Austria. pp.128-132. ⟨hal-00459657⟩
121 View
0 Download

Share

Gmail Mastodon Facebook X LinkedIn More