Automatic Speech Recognition With a Modified Ephraim–Malah Rule

Abstract : —A soft decision gain modification is introduced and applied to the Ephraim–Malah gain function based on maximum mean-square-error estimation after amplitude compression. Non-linear evaluations of the noise overestimation factor and spectral floor are used in the same way for the proposed gain modification and for nonlinear spectral subtraction (NSS). Consistent and statistically significant automatic speech recognition improvements of the proposed approach with respect to NSS are observed for different noise conditions considered in the Aurora-2 and Aurora-3 corpora. As the nonlinearity affects the two approaches in the same way, the result of comparison is particularly interesting.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01317173
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon <>
Submitted on : Wednesday, May 18, 2016 - 10:49:38 AM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM

Identifiers

Collections

Citation

Roberto Gemello, Franco Mana, Renato de Mori. Automatic Speech Recognition With a Modified Ephraim–Malah Rule. IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2006, ⟨10.1109/LSP.2005.860535⟩. ⟨hal-01317173⟩

Share

Metrics

Record views

136