logo Idiap Research Institute        
 [BibTeX] [Marc21]
Unsupervised Spectral Substraction for Noise-Robust ASR
Type of publication: Idiap-RR
Citation: lathoud-rr-05-42
Number: Idiap-RR-42-2005
Year: 2005
Institution: IDIAP
Address: Martigny, Switzerland
Note: Published in Proceedings of the 2005 IEEE ASRU Workshop
Abstract: This paper proposes a simple, computationally efficient \mbox{2-mixture} model approach to discriminate between speech and background noise at the magnitude spectrogram level. It is directly derived from observations on real data, and can be used in a fully unsupervised manner, with the EM algorithm. In this paper, the 2-mixture model is used in an ``Unsupervised Spectral Substraction'' scheme that can be applied as a pre-processing step for any acoustic feature extraction scheme, such as MFCCs or PLP. The goal is to improve noise-robustness of the acoustic features. Experimental results on both OGI~Numbers~95 and Aurora~2 tasks yielded a major improvement on all noise conditions, while retaining a similar performance on clean conditions.
Userfields: ipdinar={2005}, ipdmembership={speech}, language={English},
Projects Idiap
Authors Lathoud, Guillaume
Magimai.-Doss, Mathew
Mesot, Bertrand
Bourlard, Hervé
Crossref by lathoud05e
Added by: [UNK]
Total mark: 0
  • rr-05-42.pdf
  • rr-05-42.ps.gz