Prediction of Cepstral Excitation Pulses for Voice Conversion

Fadoua Bahja 1 Joseph Di Martino 2 El Hassan Ibn Elhaj 3 Driss Aboutajdine 1
1 GSCM-LRIT - Laboratoire de Recherche en Informatique et Télécommunications [Rabat]
2 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
3 INPT - Institut National de Postes et Télécommunications [Rabat]
Abstract : Voice conversion is one of useful techniques to enhance pathological speech to be perceived as normal speech, although it concerns also the modifications of normal source speaker's speech to be perceived as if a target speaker had uttered it. The parameters to be converted are obtained by matching the spectral envelope of the vocal tract for the source and the target speech. Gaussian Mixture Models (GMMs) parameters are determined for providing conversion functions. The main contribution of our study consists in the prediction of Fourier cepstrum coefficients related to the excitation signal. Such a prediction leads to a satisfactory voice conversion system. Subjective perceptual results indicate that the proposed approach yields significant improvements in quality of the converted voice.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download
https://hal.inria.fr/hal-00761776
Contributor : Joseph Di Martino <>
Submitted on : Monday, December 10, 2012 - 9:43:12 AM
Last modification on : Thursday, January 11, 2018 - 6:19:56 AM
Long-term archiving on: Monday, March 11, 2013 - 11:21:25 AM

File

article_siie_2012_Bahja_Fadoua...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00761776, version 1

Collections

CNRS | INRIA | LORIA | UNIV-LORRAINE

Citation

Fadoua Bahja, Joseph Di Martino, El Hassan Ibn Elhaj, Driss Aboutajdine. Prediction of Cepstral Excitation Pulses for Voice Conversion. 5th. International Conference on Information Systems and Economic Intelligence - SIIE ̓ 2012, Feb 2012, Djerba, Tunisia. ⟨hal-00761776⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

1577

Files downloads

283

 

 

Contact

archive-ouverte@inria.fr