Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Vector Taylor Series Based Joint Uncertainty Decoding

Haitian Xu (1), Luca Rigazio (2), David Kryze (2)

(1) Aalborg University, Denmark; (2) Panasonic San Jose Laboratory, USA

Joint uncertainty decoding has recently achieved promising results by using front-end uncertainty in the back-end in a mathematically consistent framework. One drawback of the method is that it relies on stereo-data or numerical algorithms, such as DPMC, which have high computational complexity and are difficult to deploy in real applications. We propose a Vector Taylor Series (VTS) approach to joint uncertainty decoding which provides a closed-form solution to the key problem of estimating the clean/noisy speech cross-covariance matrix. Our solution does not require stereo-data or numerical integration. We also propose a new strategy to deal with the cross-covariance matrix singularity. Experiments on Aurora2 show that VTS-based joint uncertainty decoding has similar accuracy compared to DPMC-based joint uncertainty decoding while being at least three times faster. Finally, VTS-based joint uncertainty decoding provided more than 2% absolute improvement when combined with our new strategy for cross-covariance singularity.

Full Paper

Bibliographic reference.  Xu, Haitian / Rigazio, Luca / Kryze, David (2006): "Vector taylor series based joint uncertainty decoding", In INTERSPEECH-2006, paper 1688-Tue2BuP.9.