7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Computationally Efficient Noise Compensation for Robust Automatic Speech Recognition Assessed Under the Aurora 2/3 Framework

Nicholas W. D. Evans, John S. Mason

University of Wales Swansea, U.K.

In the context of mobile telephony there is a need for low resource, computationally efficient noise compensation and speech enhancement approaches. This paper assesses the performance of efficient quantile-based noise estimation integrated into a nonlinear spectral subtraction framework. The approach has been implemented in realtime with minimal latency on a 500Mhz processor and is well within the processing capabilities. Experiments are reported on the AURORA 2 and AURORA 3 corpa. Results show an average relative improvement of 15% on the clean and multi-condition training sets of the AURORA 2 database and an overall average relative improvement of 20% across the four AURORA 3 databases. It is acknowledged that these are not state-of-the-art results and further optimisation is anticipated.


Full Paper

Bibliographic reference.  Evans, Nicholas W. D. / Mason, John S. (2002): "Computationally efficient noise compensation for robust automatic speech recognition assessed under the Aurora 2/3 framework", In ICSLP-2002, 485-488.