An Improved Signal Subspace Algorithm for Speech Enhancement - Digital Services and Information Intelligence Access content directly
Conference Papers Year : 2014

An Improved Signal Subspace Algorithm for Speech Enhancement

Xuzheng Dai
  • Function : Author
  • PersonId : 985676
Baoxian Yu
  • Function : Author
  • PersonId : 985677
Xianhua Dai
  • Function : Author
  • PersonId : 985678

Abstract

Most of the algorithms for speech enhancement are designed to improve the speech listening comfort. However the frequency spectrum character is destroyed seriously after the speech enhancement. To achieve better speech listening comfort with less frequency spectral damages, we present an improved signal subspace algorithm for speech enhancement. Compared with the traditional signal space method, the improved algorithm can decrease the Mel-frequency Cepstral Coefficients (MFCC) distance, an evaluation measure which means less frequency spectral damages to the voice and keep the voices’ intelligence at the same time. Besides, the method can enlarge the distance of the easily confused voices, which means the improvement of the voice recognition ratio. Thus we get the purpose of the speech enhancement. The improved algorithm is used in a speech recognition program and has a good performance.
Fichier principal
Vignette du fichier
978-3-662-45526-5_10_Chapter.pdf (4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01342134 , version 1 (05-07-2016)

Licence

Attribution

Identifiers

Cite

Xuzheng Dai, Baoxian Yu, Xianhua Dai. An Improved Signal Subspace Algorithm for Speech Enhancement. 13th Conference on e-Business, e-Services and e-Society (I3E), Nov 2014, Sanya, China. pp.104-114, ⟨10.1007/978-3-662-45526-5_10⟩. ⟨hal-01342134⟩
72 View
260 Download

Altmetric

Share

Gmail Facebook X LinkedIn More