| Paper: | SPTM-P7.1 | ||
| Session: | Signal Enhancement and Reconstruction | ||
| Time: | Thursday, May 20, 09:30 - 11:30 | ||
| Presentation: | Poster | ||
| Topic: | Signal Processing Theory and Methods: Signal Restoration, Reconstruction, and Enhancement | ||
| Title: | CANCELLING CONVOLUTIVE AND ADDITIVE COLOURED NOISES FOR SPEECH ENHANCEMENT | ||
| Authors: | William Bobillet; Equipe Signal et Image, UMR 5131 LAP | ||
| Eric Grivel; Equipe Signal et Image, UMR 5131 LAP | |||
| Mohamed Najim; Equipe Signal et Image, UMR 5131 LAP | |||
| Roberto Guidorzi; Università di Bologna | |||
| Abstract: | In the framework of speech enhancement, many approaches have been developed when the speech signal is only corrupted by an additive noise. However, in an auditorium, when echoes appear, spatial transformations between the sources and the microphones must be considered. For this reason, we propose in this paper to deal with a speech contaminated both by convolutive and additive coloured noises.The two-microphone based noise canceller we present operates as follows: firstly, a pre-whitening step is carried out. Secondly, the blind deconvolution method we use makes it possible to estimate the finite impulse responses (FIR), their orders and the variances of the additive noises, which is a great advantage. Then, the filtered versions of speech, estimated by means of a subspace method, are used to retrieve the original speech.Index Terms - speech enhancement, convolutive noise, additive noise, blind deconvolution, subspace methods | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops